fix(audio-cpp): bundle rocRoller for ROCm

ROCm 7.2 links rocBLAS consumers to librocroller.so.1. Add that runtime family to the ROCm bundle so packaged backends resolve the dependency.

Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.agents/ai-coding-assistants.md

@@ -49,40 +49,6 @@ AI agents MUST NOT add `Co-Authored-By` trailers for themselves either.
 A human reviewer owns the contribution; the AI's involvement is recorded
 via `Assisted-by` (see below).
 
-### Exception: automation operated by a maintainer
-
-The rule above addresses the common case, an AI assistant helping a human
-contributor who then signs off. It does not fit automation that a
-maintainer runs themselves, which opens pull requests with no human
-submitter to sign. Applied literally there, nothing ever signs and the
-DCO check blocks the pull request permanently.
-
-A maintainer-operated bot MUST therefore add a `Signed-off-by` trailer
-naming **the maintainer who operates it**, not the bot and not the model:
-
-```
-Assisted-by: Codex:gpt-5
-Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
-```
-
-This is not the AI certifying the DCO. The maintainer is, exactly as they
-do for a commit they typed by hand: they configured the automation, they
-own its output, and they take responsibility for it when they merge it.
-The `Assisted-by` trailer still records that a model produced the code, so
-the provenance trail is unchanged.
-
-The exception is narrow and does not widen the rule for anyone else:
-
-- It applies only to automation a LocalAI maintainer operates and whose
-  output that maintainer reviews before merge.
-- The sign-off names a real person who accepts DCO responsibility.
-- An AI assistant helping an outside contributor still MUST NOT sign off.
-  That contributor adds their own trailer.
-- A bot MUST NOT sign off on behalf of anyone other than its operator, and
-  MUST NOT add a trailer for a contributor whose branch it pushes to. If
-  automation contributes to someone else's branch, it leaves the sign-off
-  to that contributor.
-
 ## Attribution
 
 When AI tools contribute to LocalAI development, proper attribution helps

.agents/api-endpoints-and-auth.md

@@ -236,58 +236,6 @@ Use these HTTP status codes:
 
 If your endpoint should be tracked for usage (token counts, request counts), add the `usageMiddleware` to its middleware chain. See `core/http/middleware/usage.go` and how it's applied in `routes/openai.go`.
 
-## Control-plane database health metrics
-
-In distributed mode the frontend registers three OpenTelemetry gauges over the
-PostgreSQL control-plane database (`core/services/monitoring/control_plane_db.go`,
-wired in `core/application/distributed.go`). They reach `/metrics` through the
-same Prometheus exporter as the rest of the API metrics.
-
-| Metric | Meaning | Page when |
-|--------|---------|-----------|
-| `localai_control_plane_oldest_xmin_age` | Transactions elapsed since the oldest snapshot any backend still holds | above a few million, and rising |
-| `localai_control_plane_longest_transaction_seconds` | Age of the longest open transaction | above 3600 |
-| `localai_control_plane_dead_tuple_ratio` | Dead tuples per live tuple, labelled by `table`, on `backend_nodes`, `node_models` and `gallery_operations` | sustained above ~10 on a small table |
-
-A sustained high `localai_control_plane_oldest_xmin_age` is the one to page on.
-While it grows, autovacuum can reclaim nothing anywhere in the database no
-matter how often it runs, so the dead tuple ratio keeps climbing and a six-row
-registry table can reach hundreds of megabytes. Tuning autovacuum does not help.
-The fix is to find the transaction holding the horizon open and clear it:
-
-```sql
-SELECT pid, state, age(backend_xmin) AS xmin_age, now() - xact_start AS xact_age, query
-FROM pg_stat_activity
-WHERE backend_xmin IS NOT NULL
-ORDER BY age(backend_xmin) DESC;
-```
-
-Then `pg_terminate_backend(pid)` on the offenders, and `VACUUM (VERBOSE)` the
-bloated tables once the horizon has moved.
-
-**A healthy-looking xmin age does not on its own prove the horizon is free.**
-The gauge reads `pg_stat_activity`, which only sees live backends. Two other
-things pin the very same horizon and are invisible there, so either one can hold
-vacuum back while the gauge reads 0:
-
-```sql
-SELECT gid, prepared, database, transaction FROM pg_prepared_xacts;
-SELECT slot_name, active, xmin, catalog_xmin FROM pg_replication_slots;
-```
-
-An orphaned prepared transaction is cleared with `ROLLBACK PREPARED '<gid>'`,
-and a stale slot with `pg_drop_replication_slot('<slot_name>')`. Check both
-before concluding that a bloated table has some other cause.
-
-Sampling is scrape-driven behind a 30 second cache, so scrape frequency does not
-translate into database load. Failed and timed-out samples cost the same interval
-as successful ones, so a database that is already struggling is not retried on
-every scrape. A failed sample reports the last good values rather than failing the
-scrape, because these gauges matter most when the database is struggling. Before
-the first successful sample the gauges are absent rather than zero, since a zero
-xmin age would read as a healthy horizon: alert on `absent()` too if you need to
-distinguish "healthy" from "never sampled".
-
 ## Advertising surfaces — where to register a new capability
 
 Beyond routing and auth, LocalAI publishes its capability surface in **four independent places**. When you add an endpoint — especially one introducing a net-new capability like a new media type or a new auth-gated feature — you must update every relevant surface. These aren't optional: missing them means the endpoint works but is invisible to clients, admins, and the UI.

.agents/building-and-testing.md

@@ -45,26 +45,3 @@ Rules (both gates):
 - **Don't weaken the gate:** never hand-lower a baseline or widen a tolerance to turn a red gate green. The ratchet only moves up.
 - If a change drops coverage, **add tests** (sort `coverage-summary.json` by line% ascending to find untested code) rather than editing the baseline. When coverage legitimately rises, commit the regenerated baseline (`make test-coverage-baseline` / `test-ui-coverage-baseline`).
 - The Go gate is **strict — no tolerance**; `covermode=atomic` keeps it deterministic. The UI gate keeps a small tolerance only because its e2e coverage isn't.
-
-## Distributed-mode test suites
-
-Two suites cover distributed mode (frontend replicas, worker nodes, PostgreSQL), split by a Ginkgo label. Neither starts a message broker: a distributed deployment needs PostgreSQL and the frontends' own HTTP listener, and the `nats-io` modules are not in the build.
-
-- `make test-e2e-distributed` runs `Distributed && !VLLMMultinode && !Cluster` over `./tests/e2e/distributed` recursively. Services are wired directly into the test binary. 231 specs in about 2m20s (measured 133.3s for the main suite plus the 8 argument-validation specs in the subpackage).
-- `make test-e2e-cluster` runs `Cluster` and spawns real `local-ai` child processes through the `tests/e2e/distributed/cluster` helper package. It **builds `./local-ai` itself** (the `e2e-binary` target), so you do not run `make build` first and cannot forget to. 26 specs, 933.8s of specs in a 15m37s target run (four measurements; the suite grew from 6 specs and roughly 509s, then 21 specs and 802.5s, then 24 specs and 897 to 907s, so budget on the newest number).
-
-Both jobs live in `.github/workflows/tests-e2e-distributed.yml`, with `timeout-minutes: 45` each. They trigger on pull requests *and* on every push to `master`; the `paths-ignore` filter (see [.agents/ci-caching.md](ci-caching.md)) sits on the pull-request trigger only, so a master push always runs both. They are advisory only because `master` carries no branch protection, which is a repository setting and not a YAML key: `continue-on-error: true` would flip the run's *conclusion* to success and hide the failure, so it is not used.
-
-- **The container is suite-scoped, not spec-scoped.** `SetupInfra` used to start a PostgreSQL (~10s) and a broker (~3.5s) per spec. Across the 213 specs behind it that was roughly **48 minutes of pure container startup per run**, which is why this suite was never in CI. (213 rather than the ~240 above: the larger number is everything the label filter selects, the smaller one is just the specs that call `SetupInfra`.) The broker container is gone entirely, and the PostgreSQL one now starts once in `BeforeSuite` with each spec getting its own database via `CREATE DATABASE` (~67ms), which is what the `dbName` argument was always describing. Adding a spec needs no change: call `SetupInfra("some-name")` as before, the name is a prefix and a counter keeps it unique.
-- **Consequence for new specs:** a fan-out carrier is *shared* within a Ginkgo process, so a wildcard subscriber can observe another spec's traffic. Filter assertions on an identifier your spec owns (a node ID, a job ID) instead of counting everything on `jobs.*.progress`, and verify the spec with `--randomize-all`.
-- **`BeforeSuite`, not `SynchronizedBeforeSuite`.** Under `ginkgo -p` each process then gets its own container, keeping each process's carrier isolated. A single shared database across parallel processes would let specs on different processes see each other's messages on the same subject.
-- **The label split.** The 8 argument-validation specs under `tests/e2e/distributed/cluster/` carry `Label("Distributed")` only, on purpose: they need no binary and no PostgreSQL, so they belong in the fast job. That is why `test-e2e-distributed` keeps `-r` (it must reach the subpackage) and `test-e2e-cluster` deliberately does **not** (the subpackage is out of its scope).
-- **The binary is built, and a stale one is refused.** `test-e2e-cluster` used to take `./local-ai` as given and only check that a file by that name existed. An edit that was never rebuilt therefore ran the entire suite against an older build while reporting on the working tree, which surfaced once as a spec failing on caller line numbers that matched no line in any source file. Two things close it. The target depends on `e2e-binary`, which is `go build -o local-ai ./cmd/local-ai` and not `make build` (that one also builds the React UI, which this suite never touches and CI stubs). And `localAIBinary` in the harness **fails**, on a developer box as well as under CI, when the binary is older than the newest non-test Go source in the tree, which covers a run started with `LOCALAI_E2E_BINARY` or by invoking ginkgo directly. `_test.go` files are excluded from that scan on purpose: they compile into the ginkgo suite and never into `local-ai`, so counting them would fire on every edit to the spec being run. Set `LOCALAI_E2E_BINARY` to opt out of the build; there is no opt-out of the staleness check, because a rebuild is the remedy.
-- **`--fail-on-empty` is load-bearing on both targets.** Ginkgo exits 0 when a label filter selects nothing, so without it a refactor that renames or drops `Label("Cluster")` leaves the target reporting "Test Suite Passed" having started no cluster at all. `LOCALAI_E2E_REQUIRE_BINARIES` does not cover this case: it only fires inside a spec that is actually running.
-- **The binary gate.** `localAIBinary()` and `mockBackendBinary()` **fail** rather than skip when `CI` is set, or when `LOCALAI_E2E_REQUIRE_BINARIES` is truthy; `LOCALAI_E2E_REQUIRE_BINARIES=0` (also `off`, `no`, `n`, `disabled`, and anything `strconv.ParseBool` reads as false) forces skipping even under CI. **Any value that parses as neither reads as ON**, not off: setting the variable to something meaningless means someone meant to turn the gate on, and reading it as false would quietly restore the silent skip the flag exists to remove. The whole polarity is deliberate, because in CI a skipped cluster spec is indistinguishable from a passing one: Ginkgo exits 0 on skips. Locally a missing binary still just skips, since `CI` is unset in an ordinary shell.
-- **Flake budget: no retries at all.** `--flake-attempts` is *total attempts*, not retries (ginkgo v2.29.0 `internal/group.go` sets `maxAttempts = FlakeAttempts` and loops `attempt < maxAttempts`; the flag's own usage string reads "0 - failed tests are not retried"). `DISTRIBUTED_TEST_FLAKES` defaults to **1**, so each spec runs once and a failure is a failure, and `test-e2e-cluster` pins `--flake-attempts 1` outright rather than reading the variable. The repo-wide `TEST_FLAKES=5` means up to five attempts, so up to four retries. These suites exist to surface nondeterminism, and a retry converts exactly that signal into a green run. Raise it locally when bisecting something unrelated, not in the Makefile.
-- **Coverage:** `tests/e2e/distributed` is excluded from the coverage roots (`COVERAGE_E2E_ROOTS = ./tests/e2e`, run non-recursively), and so is the `cluster` helper package beneath it. Neither suite moves the baseline, so production code that these suites are the only cover for reads as **uncovered**. Unit tests for such code belong under `./core/...` with `testutil.SetupTestDB()`.
-- **The cluster job builds against a stubbed React UI.** `core/http/react-ui/dist` is gitignored and built by Node, so the workflow writes a one-line `index.html` there to satisfy the `//go:embed react-ui/dist/*` in `core/http/app.go` and skips a full Node and Vite install. That holds only while the suite drives the HTTP API and never the UI, which has its own e2e suite. A spec that ever asserts on a UI asset would pass locally, where a real `dist/` exists, and be served the stub in CI: if you write one, the stub step has to go and the real build come back.
-- **The topology that matters is two frontends and two workers.** `cluster_busless_test.go` runs the whole programme on it, and it is the only shape in which the OWNER path and the RELAY path are live at the same time: with the two workers' tunnels landing on different replicas, every request either goes to the replica holding that worker's tunnel or is relayed through the one that does. A one-worker cluster cannot tell those apart, and cannot state that killing a replica re-homes only ITS worker. Which worker served a request is read back from `node_models` rather than assumed, and the two models are pinned to one worker each through the admin API (`PUT /api/nodes/:id/labels` plus `POST /api/nodes/scheduling`), so a selector that failed open reddens the spec instead of hiding in it.
-- **The fan-out carrier is proven under real binaries by `cluster_fanout_test.go`.** Both specs run two frontends and no workers against one PostgreSQL, publish at frontend 0 and read at frontend 1, and cost 7.0s together. They drive a gallery operation on purpose: `GET /models/jobs/<id>` answers from `galleryop`'s in-memory statuses map, which on a peer replica is filled by the `gallery.*.progress` subscriber and by nothing else (`Hydrate` runs once at startup, long before these operations exist), so a peer that answers was told over the carrier. Every other broadcast family has a durable table behind it that a peer would converge through anyway, and a spec on one of those cannot separate "the broadcast arrived" from "the row was read". The specs make that checkable rather than argued: the `gallery_operations` row is written when the gallery worker DEQUEUES an operation, so an operation still queued has none, and both specs assert zero rows while the peer is already answering with the operation's own bytes. Holding the queue is what `cluster.Options.Galleries` is for: it points every frontend at one gated index and turns the startup estimate warmer off, so the operation the spec submits is parked inside a fetch only the spec can complete. The second spec adds the oversized path: an element name of 9000 bytes puts the encoded notification past PostgreSQL's 8000-byte cap (exclusive), so the broadcast becomes a `bus_messages` row plus a notification carrying its id, and the spec asserts the row exists, decodes it, and compares its element name byte for byte with what frontend 1 answers. A one-byte control operation in the same run is asserted to leave NO row, which is what keeps "a row exists" a statement about size rather than one that is true of every operation.
-- **Do not shorten the cluster suite's waits.** Three of its six specs sit at ~167s each because they wait out a 60s staleness threshold plus a 15s health-check tick. That wait is what stops the assertions from passing before the system could have reacted, which was a real false green earlier on. If the job has to get faster, the levers are CI concurrency or making the thresholds configurable, not shorter waits.

.agents/ci-caching.md

@@ -153,7 +153,7 @@ This is worth more than it looks. Measured over the week to 2026-07-30, **97% of
 
 The volume is real: 13 gallery-only PRs merged that week with 10 open at once, and 78 of the 137 PRs opened were bot-generated.
 
-`paths-ignore` on the PR trigger of `image-pr.yml` (7 jobs), `build-test.yaml` (3), `lint.yml` (2) and `tests-e2e.yml` (1) drops 13 of those 20, measured before `tests-e2e-distributed.yml` (2 jobs) landed. That workflow carries the same exclusion set for the same reason: its dependency graph is 99 packages, so an allowlist of paths would silently stop guarding the moment code moved, while a diff confined to the paths below provably cannot reach it. The excluded set:
+`paths-ignore` on the PR trigger of `image-pr.yml` (7 jobs), `build-test.yaml` (3), `lint.yml` (2) and `tests-e2e.yml` (1) drops 13 of those 20. The excluded set:
 
 | Path | Why no image or Go build can see it |
 |---|---|
@@ -192,7 +192,7 @@ What still runs, and why it has to:
 Two properties this relies on:
 
 - `paths-ignore` skips a run only when **every** changed file matches, so a PR touching the gallery *and* Go code still runs everything. That is what makes the exclusion safe rather than a hole.
-- `master` carries no branch protection and no rulesets, so a skipped workflow reports no status and nothing waits on it. If required status checks are ever introduced, these five entries must be excluded from the required set or PRs will hang on "Expected — Waiting for status to be reported".
+- `master` carries no branch protection and no rulesets, so a skipped workflow reports no status and nothing waits on it. If required status checks are ever introduced, these four entries must be excluded from the required set or PRs will hang on "Expected — Waiting for status to be reported".
 
 ### `image.yml` on master push is gated too, by a job rather than a path filter
 

.agents/ds4-backend.md

@@ -77,56 +77,6 @@ spectrum. **Metal (Darwin) only** - it is a no-op on CUDA/CPU. Enable with
 budget). Gallery entries built on this: `deepseek-v4-flash-q4-ssd` (153 GB Flash
 on a 128 GB Mac) and `deepseek-v4-pro-q2-ssd` (433 GB Pro, experimental).
 
-## CUDA architecture (do not build without one)
-
-`backend/cpp/ds4/Makefile` drives upstream's **object targets** directly
-(`$(MAKE) -C ds4 ds4.o ds4_cuda.o ...`), which bypasses upstream's own guard:
-its `cuda` target refuses to build unless `CUDA_ARCH` is set, and offers
-`cuda-spark` (sm_121, DGX Spark / GB10) and `cuda-generic` (native) instead.
-Built with no `-arch`, nvcc targets its default architecture and the kernels run
-as JIT'd PTX. On GB10 that silently corrupted every prefill batch of >=128
-tokens - the model emitted text unrelated to the prompt and never closed its
-thinking block, so `content` came back empty - and cost close to two orders of
-magnitude of prefill throughput (4.21 t/s vs 325.70 t/s, same box, same model).
-Short prompts stayed correct, which is why it went unnoticed.
-
-The Makefile therefore picks a gencode list from `CUDA_MAJOR_VERSION` (a build
-arg the backend matrix already declares, forwarded by `Dockerfile.ds4`) and
-`uname -m`, and passes it as `NVCC_ARCH_FLAGS` to the sub-make. Upstream's
-`CUDA_ARCH` accepts a single value, so it cannot express the fat binary the
-shipped images need; a command-line assignment beats its `:=`. An empty
-`CUDA_MAJOR_VERSION` falls back to upstream's `native` for local developer
-builds, and an unrecognised one is a hard error - no CI runner has a GPU, so a
-silent `native` there is exactly the failure mode this guards against.
-
-`DS4_CUDA_HAVE_MXF4` is deliberately unset: upstream defines it only for
-single-arch sm_120/sm_121 builds and guards it with a plain `#ifdef` rather than
-`__CUDA_ARCH__`, so it cannot be combined with older archs. It gates an optional
-MXFP4 indexer fast path whose `#ifndef` branch returns 0, so omitting it costs
-speed, not correctness.
-
-### Verifying a build
-
-Check which flags a configuration resolves to, without compiling anything:
-
-```
-make -C backend/cpp/ds4 BUILD_TYPE=cublas CUDA_MAJOR_VERSION=13 NATIVE=false \
-  --eval='show: ; @echo [$(DS4_ARCH_MAKEVARS)]' show
-```
-
-Do not use `make -n` for this: the recipe is `+$(MAKE) ...`, and the `+` prefix
-makes it run even under `-n`.
-
-Then exercise the failure mode itself against a built backend. It only appears
-above one prefill batch, so the ordinary `predict` spec cannot catch it:
-
-```
-BACKEND_BINARY=$(pwd)/backend/cpp/ds4/package/run.sh \
-BACKEND_TEST_MODEL_FILE=/path/to/ds4flash.gguf \
-BACKEND_TEST_CAPS=health,load,predict,long_prefill \
-go test -count=1 -timeout=30m -v ./tests/e2e-backends/...
-```
-
 ## Build matrix
 
 | Build | Where | Notes |

.agents/localai-assistant-mcp.md

@@ -94,4 +94,4 @@ The user chose KISS. Every mutating tool has a safety rule (`prompts/10_safety.m
 
 ## Distributed mode
 
-The in-memory MCP server runs only on the head node (where the chat handler runs). `inproc.Client` wraps services that are already distributed-aware (`GalleryService` coordinates with workers; `ListNodes` reads the PostgreSQL-backed node registry). MCP tools are not routed anywhere: the admin surface lives on the head, period.
+The in-memory MCP server runs only on the head node (where the chat handler runs). `inproc.Client` wraps services that are already distributed-aware (`GalleryService` coordinates with workers; `ListNodes` reads the NATS-populated registry). No NATS routing of MCP tools — the admin surface lives on the head, period.

.github/PULL_REQUEST_TEMPLATE.md

@@ -5,7 +5,7 @@ This PR fixes #
 **Notes for Reviewers**
 
 
-**[Signed commits](../CONTRIBUTING.md#commit-messages)**
+**[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)**
 - [ ] Yes, I signed my commits.
 - [ ] Documentation updated (docs/content/) for user-facing changes, or not applicable
  

.github/backend-matrix.yml

@@ -3208,9 +3208,10 @@ include:
   # consumed. Same reason CUDA needs its toolkit in base-image rather than in a
   # builder image: this is the ds4 shape, not the llama-cpp one.
   #
-  # No ROCm entry: upstream has no HIP configuration. No CUDA arm64 or L4T
-  # entry: upstream documents and validates CUDA on x86 only. Darwin/Metal is in
-  # the includeDarwin matrix below, built by scripts/build/audio-cpp-darwin.sh.
+  # ROCm uses upstream's HIP backend and the project-wide ROCm 7.2.1 base. No
+  # CUDA arm64 or L4T entry: upstream documents and validates CUDA on x86 only.
+  # Darwin/Metal is in the includeDarwin matrix below, built by
+  # scripts/build/audio-cpp-darwin.sh.
   #
   # No vulkan entry either, though Dockerfile.audio-cpp and the backend Makefile
   # both handle BUILD_TYPE=vulkan for local builds. Every other vulkan backend
@@ -3278,6 +3279,19 @@ include:
     dockerfile: "./backend/Dockerfile.audio-cpp"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-audio-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
+    skip-drivers: 'false'
+    backend: "audio-cpp"
+    dockerfile: "./backend/Dockerfile.audio-cpp"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: ''
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3754,19 +3768,6 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
-  - build-type: 'hipblas'
-    cuda-major-version: ""
-    cuda-minor-version: ""
-    platforms: 'linux/amd64'
-    tag-latest: 'auto'
-    tag-suffix: '-gpu-rocm-hipblas-stablediffusion-ggml'
-    runs-on: 'ubuntu-latest'
-    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
-    skip-drivers: 'false'
-    backend: "stablediffusion-ggml"
-    dockerfile: "./backend/Dockerfile.golang"
-    context: "./"
-    ubuntu-version: '2404'
   - build-type: 'sycl_f16'
     cuda-major-version: ""
     cuda-minor-version: ""

.github/bump_vllm_metal.sh

@@ -3,9 +3,9 @@
 # darwin (Apple Silicon) install path. The macOS/Metal build
 # (backend/python/vllm/install.sh, Darwin branch) installs vllm-metal, which is
 # version-locked to a specific vLLM source release. install.sh derives that vLLM
-# version, and the wheel asset name, at build time from the pinned tag, so there
-# is only ONE value to bump here -- mirroring bump_vllm_wheel.sh, which bumps the
-# Linux cu130 wheel pin.
+# version at build time from vllm-metal's own installer at the pinned
+# tag, so there is only ONE value to bump here -- mirroring bump_vllm_wheel.sh,
+# which bumps the Linux cu130 wheel pin.
 #
 # This deliberately tracks vllm-project/vllm-metal, NOT vllm-project/vllm: the
 # darwin build can only use the exact vLLM version vllm-metal supports, so it may
@@ -23,20 +23,15 @@ if [ -z "$FILE" ] || [ -z "$REPO" ] || [ -z "$VAR" ]; then
     exit 1
 fi
 
-# vllm-metal ships frequent .dev releases, flagged as prereleases, alongside the
-# stable ones. /releases/latest skips the prereleases and returns the newest
-# stable tag, which is what darwin should pin: upstream deletes and re-cuts .dev
-# tags, and a pin to a deleted tag 404s the whole build.
+# vllm-metal ships frequent dev releases, all flagged as non-prerelease, so
+# /releases/latest returns the newest one (with its cp312 wheel asset).
 LATEST_TAG=$(gh_curl -H "Accept: application/vnd.github+json" \
     "https://api.github.com/repos/$REPO/releases/latest" \
     | python3 -c "import json,sys; print(json.load(sys.stdin)['tag_name'])")
 
-# The coupled vLLM release lives in .github/vllm-release-tag.commit at that tag
-# (since vllm-metal 0.28); releases predating that file pinned it inline in their
-# own install.sh. The extractor reads both forms.
-NEW_VLLM_VERSION=$( { gh_curl \
-    "https://raw.githubusercontent.com/$REPO/$LATEST_TAG/.github/vllm-release-tag.commit" \
-    || gh_curl "https://raw.githubusercontent.com/$REPO/$LATEST_TAG/install.sh"; } \
+# The coupled vLLM source version lives in vllm-metal's installer at that tag.
+NEW_VLLM_VERSION=$(gh_curl \
+    "https://raw.githubusercontent.com/$REPO/$LATEST_TAG/install.sh" \
     | "$(dirname "${BASH_SOURCE[0]}")/../scripts/lib/extract-vllm-metal-version.sh")
 
 if [ -z "$LATEST_TAG" ] || [ -z "$NEW_VLLM_VERSION" ]; then

.github/dependabot.yml

@@ -29,6 +29,10 @@ updates:
     schedule:
       # Check for updates to GitHub Actions every weekday
       interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/backend/python/bark"
+    schedule:
+      interval: "weekly"
   - package-ecosystem: "pip"
     directory: "/backend/python/common/template"
     schedule:
@@ -51,10 +55,30 @@ updates:
     ignore:
     - dependency-name: "torch"
     - dependency-name: "transformers"
+  - package-ecosystem: "pip"
+    directory: "/backend/python/exllama"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/backend/python/exllama2"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/backend/python/mamba"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/backend/python/openvoice"
+    schedule:
+      interval: "weekly"
   - package-ecosystem: "pip"
     directory: "/backend/python/rerankers"
     schedule:
       interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/backend/python/sentencetransformers"
+    schedule:
+      interval: "weekly"
   - package-ecosystem: "pip"
     directory: "/backend/python/transformers"
     schedule:
@@ -62,4 +86,44 @@ updates:
   - package-ecosystem: "pip"
     directory: "/backend/python/vllm"
     schedule:
-      interval: "weekly"
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/examples/chainlit"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/examples/functions"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/examples/langchain/langchainpy-localai-example"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/examples/langchain-chroma"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip"
+    directory: "/examples/streamlit-bot"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "docker"
+    directory: "/examples/k8sgpt"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "docker"
+    directory: "/examples/kubernetes"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "docker"
+    directory: "/examples/langchain"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "gomod"
+    directory: "/examples/semantic-todo"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "docker"
+    directory: "/examples/telegram-bot"
+    schedule:
+      interval: "weekly"

.github/workflows/bump_deps.yaml

@@ -166,7 +166,7 @@ jobs:
           push-to-fork: ci-forks/LocalAI
           commit-message: ':arrow_up: Update ${{ matrix.repository }}'
           title: 'chore: :arrow_up: Update ${{ matrix.repository }} to `${{ steps.bump.outputs.commit }}`'
-          branch: "bump/${{ matrix.variable }}"
+          branch: "update/${{ matrix.variable }}"
           body: ${{ steps.bump.outputs.message }}
           signoff: true
 
@@ -203,7 +203,7 @@ jobs:
           push-to-fork: ci-forks/LocalAI
           commit-message: ':arrow_up: Update vllm-project/vllm cu130 wheel'
           title: 'chore: :arrow_up: Update vllm-project/vllm cu130 wheel to `${{ steps.bump.outputs.commit }}`'
-          branch: "bump/VLLM_VERSION"
+          branch: "update/VLLM_VERSION"
           body: ${{ steps.bump.outputs.message }}
           signoff: true
 
@@ -241,6 +241,6 @@ jobs:
           push-to-fork: ci-forks/LocalAI
           commit-message: ':arrow_up: Update vllm-project/vllm-metal (darwin)'
           title: 'chore: :arrow_up: Update vllm-metal (darwin) to `${{ steps.bump.outputs.commit }}`'
-          branch: "bump/VLLM_METAL_VERSION"
+          branch: "update/VLLM_METAL_VERSION"
           body: ${{ steps.bump.outputs.message }}
           signoff: true

.github/workflows/notify-releases.yaml

@@ -31,14 +31,13 @@ jobs:
             messages: [
                 {
                 role: "system",
-                content: "Write a Discord message with a bullet point summary of the release notes. Keep the complete message under 1800 characters."
+                content: "Write a discord message with a bullet point summary of the release notes."
                 },
                 {
                 role: "user",
                 content: $input
                 }
-            ],
-            max_tokens: 450
+            ]
             }')
 
             # Send the request to LocalAI API
@@ -47,7 +46,7 @@ jobs:
             -d "$json_payload")
 
             # Extract the summary from the response
-            summary=$(printf '%s' "$response" | jq -er '.choices[0].message.content | strings | .[0:1800]')
+            summary=$(echo $response | jq -r '.choices[0].message.content')
 
             # Print the summary
             #  -H "Authorization: Bearer $API_KEY" \

.github/workflows/test.yml

@@ -80,13 +80,8 @@ jobs:
             coverage/coverage.out
             coverage/coverage.html
           if-no-files-found: ignore
-      # tmate keeps the runner busy until the 6 hour job limit, so a single
-      # failure costs a whole runner slot. Only open a session when someone
-      # asked for one by labelling the pull request `ci-debug`, and cap the
-      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
-        timeout-minutes: 30
+        if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true
@@ -130,13 +125,8 @@ jobs:
           export PATH="/opt/homebrew/opt/make/libexec/gnubin:$PATH"
           PATH="$PATH:$HOME/go/bin" make protogen-go
           PATH="$PATH:$HOME/go/bin" BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" make --jobs 4 --output-sync=target test
-      # tmate keeps the runner busy until the 6 hour job limit, so a single
-      # failure costs a whole runner slot. Only open a session when someone
-      # asked for one by labelling the pull request `ci-debug`, and cap the
-      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
-        timeout-minutes: 30
+        if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-aio.yml

@@ -77,13 +77,8 @@ jobs:
       - name: Test
         run: |
             PATH="$PATH:$HOME/go/bin" make backends/local-store backends/silero-vad backends/llama-cpp backends/whisper backends/piper backends/stablediffusion-ggml docker-build-e2e e2e-aio
-      # tmate keeps the runner busy until the 6 hour job limit, so a single
-      # failure costs a whole runner slot. Only open a session when someone
-      # asked for one by labelling the pull request `ci-debug`, and cap the
-      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
-        timeout-minutes: 30
+        if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-e2e-distributed.yml

@@ -1,206 +0,0 @@
----
-name: 'E2E Distributed Tests'
-
-on:
-  pull_request:
-    # The suite's dependency graph is 99 packages, so an allowlist of paths
-    # silently stops guarding the moment code moves. At ~75s the job is cheap
-    # enough to run unless the diff is confined to paths it provably cannot
-    # reach. See .agents/ci-caching.md.
-    paths-ignore:
-      - 'gallery/**'
-      - 'docs/**'
-      - 'examples/**'
-      - '**/*.md'
-  push:
-    branches:
-      - master
-
-concurrency:
-  group: ci-tests-e2e-distributed-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  tests-e2e-distributed:
-    runs-on: ubuntu-latest
-    # Advisory because it is deliberately not in branch protection, so a failure
-    # is a visible red X rather than a blocked merge. Promoting it to a required
-    # check is a repository-settings change, to be made once it has a track
-    # record; a heavy suite made required on day one gets disabled instead of
-    # fixed.
-    timeout-minutes: 45
-    steps:
-      - name: Clone
-        uses: actions/checkout@v7
-        with:
-          submodules: true
-      - name: Configure apt mirror on runner
-        uses: ./.github/actions/configure-apt-mirror
-      - name: Setup Go
-        uses: actions/setup-go@v5
-        with:
-          go-version: '1.26.0'
-          cache: false
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y build-essential libopus-dev
-      - name: Proto Dependencies
-        run: |
-          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
-          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
-          rm protoc.zip
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
-          PATH="$PATH:$HOME/go/bin" make protogen-go
-      - name: Pre-pull test images
-        # Pulling here rather than inside the suite keeps container-start timing
-        # out of the spec timeouts and makes a registry outage read as a
-        # setup failure instead of a test failure. This is the only image the
-        # suite needs once the testcontainers reaper is disabled below: the
-        # suite stands up no message broker, because nothing under test dials
-        # one.
-        run: |
-          docker pull postgres:16-alpine
-      - name: Distributed E2E
-        # TESTCONTAINERS_RYUK_DISABLED keeps the pre-pull above meaningful. The
-        # reaper exists to clean up leaked containers on a long-lived host, but
-        # this runner is ephemeral and every container dies with the VM. Leaving
-        # it enabled would pull a third, unpinned image (testcontainers/ryuk)
-        # from Docker Hub mid-suite: exactly the registry dependency the
-        # pre-pull step exists to remove.
-        env:
-          TESTCONTAINERS_RYUK_DISABLED: "true"
-        run: |
-          PATH="$PATH:$HOME/go/bin" make test-e2e-distributed
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
-
-  tests-e2e-cluster:
-    runs-on: ubuntu-latest
-    # Advisory for the same reason as the job above: master has no branch
-    # protection, so a failure here is a visible red X rather than a blocked
-    # merge. That is a repository-settings property, not a YAML key. The key
-    # that looks like it says "advisory" instead flips the run's conclusion to
-    # success, which hides the failure rather than flagging it, so it appears in
-    # none of this repo's workflows and must not be added here.
-    #
-    # Separate job from tests-e2e-distributed so the fast in-process suite is
-    # not held behind a Go build of local-ai. Serial on purpose: each Ginkgo
-    # process would get its own PostgreSQL container and each spec spawns two or
-    # three local-ai children, so --procs on an unmeasured runner is a change to
-    # make with numbers, not by default.
-    #
-    # The two timeouts bound different things and are not alternatives. Ginkgo's
-    # --timeout=20m bounds the SUITE only; this job timeout must additionally
-    # cover setup, which here is the larger and more variable half: submodule
-    # checkout, apt, protoc plus two go installs plus protogen-go, a cold-cache
-    # module download (cache: false), a full go build of ./cmd/local-ai, and a
-    # separate ginkgo test compile. That build alone is ~316s of CPU, so on a
-    # 4-vCPU runner setup is realistically 8-12 minutes.
-    #
-    # 45 minutes therefore, matching the sibling job. A tighter number does not
-    # make a hang fail faster, it just moves the kill from Ginkgo, which prints
-    # which spec hung, to the runner, which prints nothing: a red job with no
-    # evidence, which is how a suite gets disabled rather than fixed.
-    #
-    # The suite itself is about 8m30s over three consecutive runs (509.1s /
-    # 509.8s / 512.3s, so 8m29s to 8m32s) on a developer box, and will be slower
-    # here. Three specs sit at ~167s each because they wait out a 60s staleness
-    # threshold plus a 15s health-check tick (HealthCheckInterval, in
-    # core/config/distributed_config.go; core/services/nodes/health.go runs the
-    # ticker on the unexported checkInterval, not one of the reconcilers). Do
-    # not shorten those windows to make this job faster: the wait is what stops
-    # the assertions from passing before the system could have reacted, which
-    # was a real false green earlier on.
-    timeout-minutes: 45
-    steps:
-      - name: Clone
-        uses: actions/checkout@v7
-        with:
-          submodules: true
-      - name: Configure apt mirror on runner
-        uses: ./.github/actions/configure-apt-mirror
-      - name: Setup Go
-        uses: actions/setup-go@v5
-        with:
-          go-version: '1.26.0'
-          cache: false
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y build-essential libopus-dev
-      - name: Proto Dependencies
-        run: |
-          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
-          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
-          rm protoc.zip
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
-          PATH="$PATH:$HOME/go/bin" make protogen-go
-      - name: Stub the embedded React UI
-        # core/http/react-ui/dist is gitignored and built by Node, but this
-        # suite drives the HTTP API and never the UI, which has its own e2e
-        # suite. A single index.html satisfies the //go:embed react-ui/dist/*
-        # in core/http/app.go, so the job skips a full Node and Vite install.
-        # If a cluster spec ever asserts on a UI asset, this step must go and
-        # the real build come back: a developer box has a real dist/, so such a
-        # spec would pass locally and fail only here, or worse be served the
-        # stub and pass in both places.
-        run: |
-          mkdir -p core/http/react-ui/dist
-          printf '<!doctype html><title>stub</title>\n' > core/http/react-ui/dist/index.html
-      - name: Pre-pull test images
-        # Same reasoning as the job above: pulling here keeps container-start
-        # timing out of the spec timeouts and makes a registry outage read as a
-        # setup failure rather than a test failure.
-        run: |
-          docker pull postgres:16-alpine
-      - name: Cluster E2E
-        env:
-          # No LOCALAI_E2E_BINARY and no separate build step: make test-e2e-cluster
-          # builds ./local-ai itself, AFTER the protogen-go it also depends on.
-          # Building it in a step of its own put the generated .pb.go files newer
-          # than the binary, which the harness's staleness check reads, correctly,
-          # as a binary that does not contain the tree it is about to be measured
-          # against. One owner for the build is also what makes a local run and
-          # this job exercise the same bytes.
-          #
-          # Must live under the workspace so the upload step below can reach it.
-          # The harness defaults to GinkgoT().TempDir(), which lands under
-          # TMPDIR and would leave the artifact glob matching nothing.
-          LOCALAI_E2E_LOG_DIR: ${{ github.workspace }}/cluster-logs
-          # Belt and braces: the harness already fails rather than skips when CI
-          # is set, and GitHub Actions always sets CI. Stating it here means a
-          # future edit to that default cannot silently turn this job into one
-          # that passes without ever starting a cluster, since a skipped cluster
-          # spec is indistinguishable from a passing one.
-          LOCALAI_E2E_REQUIRE_BINARIES: "true"
-          # See the job above: the runner is ephemeral, so the reaper buys
-          # nothing and would pull a third, unpinned Docker Hub image mid-suite.
-          TESTCONTAINERS_RYUK_DISABLED: "true"
-        run: |
-          PATH="$PATH:$HOME/go/bin" make test-e2e-cluster
-      - name: Upload process logs
-        # The per-process logs are the only way to read a cluster failure: the
-        # Ginkgo output says which assertion failed, not what the four child
-        # processes were doing. Without this a red job is undebuggable.
-        if: ${{ failure() }}
-        uses: actions/upload-artifact@v7
-        with:
-          name: cluster-process-logs
-          path: cluster-logs/**/*.log
-          if-no-files-found: ignore
-          retention-days: 7
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true

.github/workflows/tests-e2e.yml

@@ -63,13 +63,8 @@ jobs:
       - name: Test Backend E2E
         run: |
           PATH="$PATH:$HOME/go/bin" make build-mock-backend test-e2e
-      # tmate keeps the runner busy until the 6 hour job limit, so a single
-      # failure costs a whole runner slot. Only open a session when someone
-      # asked for one by labelling the pull request `ci-debug`, and cap the
-      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
-        timeout-minutes: 30
+        if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-pii-ner-e2e.yml

@@ -88,13 +88,8 @@ jobs:
       # CPU and runs the token_classify capability spec (byte-offset contract).
       - name: Run live PII NER backend E2E
         run: PATH="$PATH:$HOME/go/bin" make test-extra-backend-privacy-filter
-      # tmate keeps the runner busy until the 6 hour job limit, so a single
-      # failure costs a whole runner slot. Only open a session when someone
-      # asked for one by labelling the pull request `ci-debug`, and cap the
-      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
-        timeout-minutes: 30
+        if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.github/workflows/tests-ui-e2e.yml

@@ -75,13 +75,8 @@ jobs:
           path: core/http/react-ui/coverage/
           if-no-files-found: ignore
           retention-days: 7
-      # tmate keeps the runner busy until the 6 hour job limit, so a single
-      # failure costs a whole runner slot. Only open a session when someone
-      # asked for one by labelling the pull request `ci-debug`, and cap the
-      # session so a forgotten label cannot idle a runner either.
       - name: Setup tmate session if tests fail
-        if: ${{ failure() && contains(github.event.pull_request.labels.*.name, 'ci-debug') }}
-        timeout-minutes: 30
+        if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23
         with:
           detached: true

.golangci.yml

@@ -19,22 +19,7 @@ linters:
     - staticcheck
   enable:
     - forbidigo
-    # gocritic is enabled for ONE checker: ruleguard, which runs the rules in
-    # hack/lint/. Every other gocritic check is off (disable-all below), so
-    # this adds no style noise; it is here purely as the gate that catches a
-    # gRPC backend wrapper written without Unwrap. See
-    # hack/lint/backend_wrappers.go for why that cannot be a compile-time
-    # assertion.
-    - gocritic
   settings:
-    gocritic:
-      disable-all: true
-      enabled-checks:
-        - ruleguard
-      settings:
-        ruleguard:
-          failOn: all
-          rules: '${base-path}/hack/lint/backend_wrappers.go'
     forbidigo:
       forbid:
         - pattern: '^t\.Errorf$'
@@ -141,10 +126,3 @@ linters:
       - path: ^backend/go/whisper/sources/
         text: 'http\.(DefaultClient|Get|Post|PostForm|Head)'
         linters: [forbidigo]
-      # Test doubles embed grpc.Backend to inherit the interface's method set
-      # over a NIL value; they decorate nothing, hold no inner client, and have
-      # no transport answer to forward. The rule targets production wrappers,
-      # which is where swallowing that answer deletes replica rows.
-      # gocritic here is only the backend-wrapper ruleguard rule.
-      - path: _test\.go$
-        linters: [gocritic]

AGENTS.md

@@ -8,7 +8,7 @@ Human contributors: see [CONTRIBUTING.md](CONTRIBUTING.md) for the development w
 
 LocalAI follows the Linux kernel project's [guidelines for AI coding assistants](https://docs.kernel.org/process/coding-assistants.html). Before submitting AI-assisted code, read [.agents/ai-coding-assistants.md](.agents/ai-coding-assistants.md). Key rules:
 
-- **No `Signed-off-by` from AI.** Only the human submitter may sign off on the Developer Certificate of Origin. One exception: automation a maintainer operates signs off with *that maintainer's* identity, since no other human submitter exists to certify it. See [.agents/ai-coding-assistants.md](.agents/ai-coding-assistants.md).
+- **No `Signed-off-by` from AI.** Only the human submitter may sign off on the Developer Certificate of Origin.
 - **No `Co-Authored-By: <AI>` trailers.** The human contributor owns the change.
 - **Use an `Assisted-by:` trailer** to attribute AI involvement. Format: `Assisted-by: AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2]`.
 - **The human submitter is responsible** for reviewing, testing, and understanding every line of generated code.

CONTRIBUTING.md

@@ -218,7 +218,7 @@ LocalAI follows the **same guidelines as the Linux kernel project** for AI-assis
 
 The full policy for this repository lives in [`.agents/ai-coding-assistants.md`](.agents/ai-coding-assistants.md). Summary:
 
-- **AI agents MUST NOT add `Signed-off-by` tags.** Only humans can certify the Developer Certificate of Origin. Automation operated by a maintainer is the one exception: it signs off with that maintainer's identity, because there is no other human submitter to certify it.
+- **AI agents MUST NOT add `Signed-off-by` tags.** Only humans can certify the Developer Certificate of Origin.
 - **AI agents MUST NOT add `Co-Authored-By` trailers** attributing themselves as co-authors.
 - **Attribute AI involvement with an `Assisted-by` trailer** in the commit message:
 
@@ -265,37 +265,6 @@ The e2e tests run LocalAI in a Docker container and exercise the API:
 make test-e2e
 ```
 
-### Running distributed-mode tests
-
-Distributed mode (several frontend replicas, worker nodes and PostgreSQL) has two suites. Both bring up their PostgreSQL with testcontainers, so Docker has to be available. There is no message broker to bring up: a distributed deployment needs PostgreSQL and the frontends' own HTTP listener, and nothing else.
-
-```bash
-make test-e2e-distributed   # in-process: services wired directly into the test binary
-make test-e2e-cluster       # process-level: real local-ai child processes
-```
-
-`make test-e2e-distributed` is the fast one (231 specs in roughly 2m20s). It starts one PostgreSQL for the whole run and gives each spec its own database. It runs each spec exactly once, with no retry: `DISTRIBUTED_TEST_FLAKES` defaults to 1 and feeds ginkgo's `--flake-attempts`, which counts *total attempts*, not retries. That is deliberately below the repo-wide `TEST_FLAKES=5`, because this suite exists to catch nondeterministic cluster behaviour and a retry hides exactly the failure it is meant to catch. Raise it locally when bisecting something unrelated.
-
-`make test-e2e-cluster` runs `local-ai` as real child processes, one per frontend replica and one per worker, so a spec can kill a replica and assert what the survivors do. Budget about 13m30s (one measurement: 802.5s of specs in a 13m26s target run, which includes building the binary): several of its 21 specs wait out real staleness and health-check windows. An earlier record of 6 specs and roughly 509s is superseded. It needs a built binary and the mock backend:
-
-```bash
-make build build-mock-backend
-make test-e2e-cluster
-```
-
-Two environment variables steer it:
-
-| Variable | Purpose |
-|---|---|
-| `LOCALAI_E2E_BINARY` | path to the `local-ai` binary (default: `local-ai` in the repository root) |
-| `LOCALAI_E2E_LOG_DIR` | directory for the per-process logs (default: a Ginkgo temp dir) |
-
-Set `LOCALAI_E2E_LOG_DIR` when debugging. A cluster failure is unreadable without the individual frontend and worker logs, and Ginkgo only tells you which assertion failed.
-
-A missing binary skips the cluster specs locally but fails them whenever `CI` is set, so a build problem cannot turn the CI job green without ever starting a cluster. `LOCALAI_E2E_REQUIRE_BINARIES=1` forces that failing behaviour anywhere; `LOCALAI_E2E_REQUIRE_BINARIES=0` forces the skip back on even under CI.
-
-Both suites run in `.github/workflows/tests-e2e-distributed.yml`, on pull requests and on every push to `master`. The `paths-ignore` filter is on the pull-request trigger only, so a master push always runs them.
-
 ### React UI tests and coverage
 
 The React UI (`core/http/react-ui/`) is covered by Playwright e2e specs, gated by a **monotonic line-coverage ratchet** (`make test-ui-coverage-check`, run in CI). The metric is non-deterministic — a fast local box reads higher than a slow CI runner for the same code — so a small tolerance is unavoidable.

Makefile

@@ -34,11 +34,6 @@ TEST_FLAKES?=5
 RANDOM := $(shell bash -c 'echo $$RANDOM')
 
 VERSION?=$(shell git describe --always --tags || echo "dev" )
-# fyne package only accepts numeric x[.y[.z]] app versions, so reduce git
-# describe output (v4.9.0, v4.9.0-14-gabc1234, or a bare sha on untagged
-# checkouts) to its numeric core; anything non-numeric falls back to 0.0.0.
-# Without this the packaged launcher reports itself as version 0.0.0 (#11673).
-LAUNCHER_APP_VERSION?=$(shell v=$$(echo "$(VERSION)" | sed -E 's/^v//; s/[+-].*$$//'); echo "$$v" | grep -qE '^[0-9]+(\.[0-9]+){0,2}$$' && echo "$$v" || echo "0.0.0")
 # go tool nm ./local-ai | grep Commit
 LD_FLAGS?=-s -w
 override LD_FLAGS += -X "github.com/mudler/LocalAI/internal.Version=$(VERSION)"
@@ -240,7 +235,7 @@ test-ci-scripts:
 ## pure stdlib on purpose so they run without any backend venv; the list is
 ## explicit because their siblings (model_identity_test) import grpc and the
 ## generated protobufs, which only exist inside a built backend.
-PYTHON_HELPER_TESTS?=python_utils_test vllm_utils_test model_utils_test mlx_utils_test parent_watch_test temp_utils_test
+PYTHON_HELPER_TESTS?=python_utils_test vllm_utils_test model_utils_test mlx_utils_test parent_watch_test
 test-python-helpers:
 	cd backend/python/common && python3 -m unittest $(PYTHON_HELPER_TESTS)
 
@@ -340,108 +335,12 @@ run-e2e-aio: protogen-go
 	@echo 'Running e2e AIO tests'
 	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts $(TEST_FLAKES) -v -r ./tests/e2e-aio
 
-# Total ginkgo attempts per spec for the distributed suite: --flake-attempts counts
-# attempts, not retries. Defaults to 1, so each spec runs once and is never retried,
-# unlike TEST_FLAKES=5. This suite exists to catch nondeterministic cluster behaviour,
-# and a retry hides exactly the failures it is meant to surface. Raise it locally if
-# you are bisecting something unrelated.
-DISTRIBUTED_TEST_FLAKES?=1
-
-# Distributed architecture e2e (PostgreSQL via testcontainers). Requires Docker.
-# There is no broker container and no NatsJWT label any more: a distributed
-# deployment needs PostgreSQL and the frontends' own HTTP listener, and this
-# suite stands up exactly that.
+# Distributed architecture e2e (PostgreSQL + NATS via testcontainers).
+# Includes NatsJWT specs (JWT-enabled NATS). Requires Docker.
 # VLLMMultinode is excluded here; use test-e2e-vllm-multinode for that.
-# Cluster is excluded too and runs in test-e2e-cluster below, which needs a
-# built binary. The argument-validation specs under tests/e2e/distributed/cluster
-# carry Label("Distributed") only, so they run here and not there, on purpose.
-# -r stays because of those: they are in a subpackage this target must reach.
-# --fail-on-empty because ginkgo exits 0 when a label filter matches nothing, so
-# without it a rename of the label would turn this target into a silent no-op
-# that still reports "Test Suite Passed".
-#
-# This target needs NO built binary and therefore has no stale-binary hole:
-# ginkgo compiles the suite from the working tree on every run, and everything
-# these specs exercise runs in that process against containers. The one target
-# in this file that does exec a prebuilt binary is test-e2e-cluster below, and
-# the reason it now BUILDS it is written there.
 test-e2e-distributed: protogen-go
-	@echo 'Running distributed e2e tests (label Distributed)'
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter='Distributed && !VLLMMultinode && !Cluster' --fail-on-empty --flake-attempts $(DISTRIBUTED_TEST_FLAKES) --timeout=40m -v -r ./tests/e2e/distributed
-
-# The local-ai binary the cluster e2e execs as its frontend and worker
-# processes.
-#
-# Deliberately not `make build`: that target also builds the embedded React UI,
-# which this suite never touches, and CI stubs core/http/react-ui/dist for
-# exactly that reason. What is left is the go build, which is incremental and
-# costs seconds when nothing changed, so making it a prerequisite of the suite
-# is cheap enough that nobody has a reason to route around it.
-#
-# LOCALAI_E2E_BINARY means the caller has its own binary and owns keeping it
-# current, so this builds nothing. The staleness check in the harness still
-# applies to it, which is the point: a binary this target did not produce is
-# precisely the one nothing else vouches for.
-.PHONY: e2e-binary
-e2e-binary: protogen-go
-	@if [ -n "$$LOCALAI_E2E_BINARY" ]; then \
-	  echo "LOCALAI_E2E_BINARY=$$LOCALAI_E2E_BINARY is set; not building $(BINARY_NAME)"; \
-	else \
-	  echo "Building $(BINARY_NAME) for the cluster e2e"; \
-	  CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./cmd/local-ai; \
-	fi
-
-# Cluster e2e: runs local-ai as real child processes (frontend replicas +
-# workers) against PostgreSQL, and kills them to assert failover.
-# It BUILDS that binary rather than checking that a file by that name exists,
-# and that is a correctness fix rather than a convenience. This target used to
-# take ./local-ai as given, so an edit to core/ that was never rebuilt left the
-# whole suite exercising an older build while reporting on the working tree. The
-# failure mode is not theoretical and not loud: it surfaced as a spec failing on
-# caller line numbers that matched no line in any source file, and it would
-# otherwise have surfaced as a green run that proved nothing. build-mock-backend
-# already rebuilds unconditionally, so ./local-ai was the only gap.
-#
-# The harness carries the other half. Building here cannot help a run started
-# with LOCALAI_E2E_BINARY or by invoking ginkgo directly, so localAIBinary also
-# FAILS when the binary it is about to exec is older than the newest non-test Go
-# source in the tree. Together: this target makes the common path correct, and
-# the harness makes every other path loud.
-#
-# The argument-validation specs in tests/e2e/distributed/cluster deliberately
-# stay in test-e2e-distributed above: they need no binary and no PostgreSQL, so
-# no -r here and that package is simply out of scope.
-#
-# --fail-on-empty is load-bearing, not tidiness. Ginkgo exits 0 when a label
-# filter selects nothing, so without it a refactor that renames or drops
-# Label("Cluster") leaves this target reporting "Test Suite Passed" having
-# started no cluster at all. LOCALAI_E2E_REQUIRE_BINARIES does not cover this:
-# it only fires inside a spec that is actually running.
-#
-# --flake-attempts is pinned to 1 rather than $(DISTRIBUTED_TEST_FLAKES), and
-# should stay there: this suite exists to catch nondeterministic cluster
-# behaviour, and a retry turns exactly that signal into a green run.
-#
-# Budget: 26 specs, measured at 933.8 seconds of Ginkgo time (15m37s wall
-# including the compile) on a fast developer box. It was 591 to 612 seconds
-# before the phase 3 control-plane specs and 800 to 830 after them; the three
-# two-frontend two-worker specs in cluster_busless_test.go added 118 to 127
-# seconds (3s, 70s and 46 to 53s), nearly all of it in the churn spec, which
-# cannot be shortened: it waits for a killed replica to leave the live set
-# (cluster.InstanceLiveness is 30s, measured at 27s) before it may assert
-# anything, and then holds a window inside the reconnect grace. The two
-# cross-replica fan-out specs added 7.0 seconds of spec time (5.0s and 2.0s):
-# they run two frontends and no workers, so they pay for no registration, and
-# what they wait on is a broadcast rather than a threshold.
-#
-# --timeout is 30m rather than 20m because of that. The margin is not slack: a
-# Ginkgo timeout kills the suite mid-spec and reports a spec name rather than a
-# cause, and 20m on a loaded CI runner was one slow health tick away from
-# turning a green suite into an unreadable red one. At 15 minutes measured, 30m
-# is still twice the budget.
-test-e2e-cluster: protogen-go build-mock-backend e2e-binary
-	@echo 'Running cluster e2e tests (label Cluster, real local-ai processes)'
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter='Cluster' --fail-on-empty --flake-attempts 1 --timeout=30m -v ./tests/e2e/distributed
+	@echo 'Running distributed e2e tests (label Distributed, incl. NatsJWT)'
+	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter='Distributed && !VLLMMultinode' --flake-attempts $(TEST_FLAKES) -v -r ./tests/e2e/distributed
 
 # vLLM multi-node DP smoke (CPU). Builds local-ai:tests and the
 # cpu-vllm backend from the current working tree, then drives a
@@ -479,29 +378,19 @@ prepare-e2e:
 run-e2e-image:
 	docker run -p 5390:8080 -e MODELS_PATH=/models -e THREADS=1 -e DEBUG=true -d --rm -v $(TEST_DIR):/models --name e2e-tests-$(RANDOM) localai-tests
 
-# Distributed subpackages have separate targets that provision PostgreSQL and
-# build the host binaries; this target exercises the container-backed API only.
 test-e2e: build-mock-backend build-cloud-proxy-backend prepare-e2e run-e2e-image
 	@echo 'Running e2e tests'
 	BUILD_TYPE=$(BUILD_TYPE) \
 	LOCALAI_API=http://$(E2E_BRIDGE_IP):5390 \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts $(TEST_FLAKES) -v ./tests/e2e
+	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts $(TEST_FLAKES) -v -r ./tests/e2e
 	$(MAKE) clean-mock-backend
 	$(MAKE) clean-cloud-proxy-backend
 	$(MAKE) teardown-e2e
 	docker rmi localai-tests
 
-# `docker stop` returns as soon as the container exits, but Docker reaps a
-# `--rm` container asynchronously after that. The `docker rmi localai-tests` in
-# test-e2e then loses the race against the reaper and fails on a still
-# referenced image, turning a green suite red. Removing the container ourselves
-# is synchronous, so the image reference is gone before we return. It also
-# covers the case where nothing is running, which `docker stop` could not
-# because it rejects an empty argument list.
 teardown-e2e:
 	rm -rf $(TEST_DIR) || true
-	@CONTAINERS=$$(docker ps -aq --filter ancestor=localai-tests 2>/dev/null); \
-	if [ -n "$$CONTAINERS" ]; then docker rm -f $$CONTAINERS || true; fi
+	docker stop $$(docker ps -q --filter ancestor=localai-tests)
 
 ########################################################
 ## Integration and unit tests
@@ -1733,7 +1622,7 @@ site-serve: site
 build-launcher-darwin:
 	rm -rf dist/LocalAI.app cmd/launcher/LocalAI.app
 	mkdir -p dist
-	cd cmd/launcher && go run fyne.io/tools/cmd/fyne@latest package -os darwin -icon ../../core/http/static/logo.png --executable $(LAUNCHER_BINARY_NAME) --app-version $(LAUNCHER_APP_VERSION)
+	cd cmd/launcher && go run fyne.io/tools/cmd/fyne@latest package -os darwin -icon ../../core/http/static/logo.png --executable $(LAUNCHER_BINARY_NAME)
 	mv cmd/launcher/LocalAI.app dist/LocalAI.app
 	bash contrib/macos/sign-and-notarize.sh sign dist/LocalAI.app
 
@@ -1760,4 +1649,4 @@ release-launcher-darwin: notarize-launcher-darwin
 	@echo "dist/LocalAI.dmg is ready"
 
 build-launcher-linux:
-	cd cmd/launcher && go run fyne.io/tools/cmd/fyne@latest package -os linux -icon ../../core/http/static/logo.png --executable $(LAUNCHER_BINARY_NAME)-linux --app-version $(LAUNCHER_APP_VERSION) && mv LocalAI.tar.xz ../../$(LAUNCHER_BINARY_NAME)-linux.tar.xz
+	cd cmd/launcher && go run fyne.io/tools/cmd/fyne@latest package -os linux -icon ../../core/http/static/logo.png --executable $(LAUNCHER_BINARY_NAME)-linux && mv LocalAI.tar.xz ../../$(LAUNCHER_BINARY_NAME)-linux.tar.xz

README.md

@@ -209,7 +209,7 @@ For older news and full release notes, see [GitHub Releases](https://github.com/
 - [Object Detection](https://localai.io/features/object-detection/)
 - [Reranker API](https://localai.io/features/reranker/)
 - [P2P Inferencing](https://localai.io/features/distribute/)
-- [Distributed Mode](https://localai.io/features/distributed-mode/): horizontal scaling on PostgreSQL, with no message broker to run
+- [Distributed Mode](https://localai.io/features/distributed-mode/) — Horizontal scaling with PostgreSQL + NATS
 - [Model Context Protocol (MCP)](https://localai.io/docs/features/mcp/)
 - [Built-in Agents](https://localai.io/features/agents/) — Autonomous AI agents with tool use, RAG, skills, SSE streaming, and [Agent Hub](https://agenthub.localai.io)
 - [Backend Gallery](https://localai.io/backends/) — Install/remove backends on the fly via OCI images

backend/Dockerfile.audio-cpp

@@ -6,13 +6,14 @@ ARG APT_PORTS_MIRROR=""
 # ASR, VAD, diarization, source separation and music generation, wrapped as a
 # LocalAI gRPC backend.
 #
-# BASE_IMAGE is ubuntu:24.04 for cpu and vulkan builds, or
-# nvidia/cuda:<ver>-devel-ubuntu24.04 for cublas builds; both ship apt and
-# Ubuntu Noble packages, and the CUDA base additionally provides
-# /usr/local/cuda. BUILD_TYPE selects the engine backend in the Makefile:
-# "" = portable CPU with all ggml CPU variants, "cublas" ->
-# -DENGINE_ENABLE_CUDA=ON, "vulkan" -> -DENGINE_ENABLE_VULKAN=ON. Darwin
-# (Metal) builds bypass this Dockerfile entirely.
+# BASE_IMAGE is ubuntu:24.04 for cpu and vulkan builds,
+# nvidia/cuda:<ver>-devel-ubuntu24.04 for cublas builds, or
+# rocm/dev-ubuntu-24.04:<ver> for hipblas builds. All ship apt and Ubuntu Noble
+# packages; the GPU bases also provide their toolkits. BUILD_TYPE selects the
+# engine backend in the Makefile: "" = portable CPU with all ggml CPU variants,
+# "cublas" -> -DENGINE_ENABLE_CUDA=ON, "hipblas" -> -DENGINE_ENABLE_HIP=ON,
+# and "vulkan" -> -DENGINE_ENABLE_VULKAN=ON. Darwin (Metal) builds bypass this
+# Dockerfile entirely.
 #
 # Upstream needs GCC 13 or newer, which ubuntu:24.04 and the CUDA 12/13
 # devel-ubuntu24.04 images all provide.
@@ -62,7 +63,7 @@ ENV BUILD_TYPE=${BUILD_TYPE} \
     APT_MIRROR=${APT_MIRROR} \
     APT_PORTS_MIRROR=${APT_PORTS_MIRROR} \
     DEBIAN_FRONTEND=noninteractive \
-    PATH=/usr/local/cuda/bin:${PATH}
+    PATH=/opt/rocm/bin:/usr/local/cuda/bin:${PATH}
 
 WORKDIR /build
 
@@ -73,7 +74,7 @@ WORKDIR /build
 # fallback of its own.
 #
 # BUILD_TYPE=vulkan additionally needs the loader headers and glslc; both are in
-# Noble. The CUDA toolkit for BUILD_TYPE=cublas comes from BASE_IMAGE.
+# Noble. The CUDA and ROCm toolkits come from their matching BASE_IMAGE.
 RUN --mount=type=bind,source=.docker/apt-mirror.sh,target=/usr/local/sbin/apt-mirror \
     sh /usr/local/sbin/apt-mirror && \
     apt-get update && \
@@ -83,6 +84,9 @@ RUN --mount=type=bind,source=.docker/apt-mirror.sh,target=/usr/local/sbin/apt-mi
     if [ "${BUILD_TYPE}" = "vulkan" ]; then \
         apt-get install -y --no-install-recommends libvulkan-dev glslc; \
     fi && \
+    if [ "${BUILD_TYPE}" = "hipblas" ]; then \
+        apt-get install -y --no-install-recommends hipblas-dev rocblas-dev; \
+    fi && \
     if [ "${TARGETARCH}" = "arm64" ]; then \
         apt-get install -y --no-install-recommends gcc-14 g++-14; \
     fi && \

backend/Dockerfile.ds4

@@ -10,7 +10,6 @@ FROM ${BASE_IMAGE} AS builder
 ARG BUILD_TYPE
 ARG TARGETARCH
 ARG TARGETVARIANT
-ARG CUDA_MAJOR_VERSION
 
 ENV BUILD_TYPE=${BUILD_TYPE} \
     DEBIAN_FRONTEND=noninteractive \
@@ -36,8 +35,7 @@ RUN apt-get update && \
 COPY . /LocalAI
 
 RUN --mount=type=cache,target=/root/.ccache,id=ds4-ccache-${TARGETARCH}-${BUILD_TYPE},sharing=locked \
-    make -C /LocalAI/backend/cpp/ds4 BUILD_TYPE=${BUILD_TYPE} \
-        CUDA_MAJOR_VERSION=${CUDA_MAJOR_VERSION} NATIVE=false grpc-server package
+    make -C /LocalAI/backend/cpp/ds4 BUILD_TYPE=${BUILD_TYPE} NATIVE=false grpc-server package
 
 FROM scratch
 COPY --from=builder /LocalAI/backend/cpp/ds4/package/. ./

backend/cpp/audio-cpp/Makefile

@@ -9,7 +9,7 @@
 # recipe is a make target (not a prepare.sh) so 'make purge && make' is a clean
 # rebuild and so the bump bot can see the pin.
 
-AUDIO_CPP_VERSION?=05e508a70e3600b01454c647cdb122133ba8e64c
+AUDIO_CPP_VERSION?=43001a7e0f452d80f4588e613f13332940dd4d3a
 AUDIO_CPP_REPO?=https://github.com/0xShug0/audio.cpp
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
@@ -77,6 +77,16 @@ endif
 
 ifeq ($(BUILD_TYPE),cublas)
     CMAKE_ARGS += -DENGINE_ENABLE_CUDA=ON "-DCMAKE_CUDA_ARCHITECTURES=$(CUDA_ARCHITECTURES)"
+else ifeq ($(BUILD_TYPE),hipblas)
+    ROCM_HOME ?= /opt/rocm
+    ROCM_PATH ?= /opt/rocm
+    export CXX=$(ROCM_HOME)/llvm/bin/clang++
+    export CC=$(ROCM_HOME)/llvm/bin/clang
+    AMDGPU_TARGETS ?= gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
+    # audio.cpp forwards GPU_TARGETS to CMake's semicolon-delimited HIP list.
+    comma := ,
+    HIP_TARGETS := $(subst $(comma),;,$(AMDGPU_TARGETS))
+    CMAKE_ARGS += -DENGINE_ENABLE_HIP=ON "-DGPU_TARGETS=$(HIP_TARGETS)"
 else ifeq ($(BUILD_TYPE),vulkan)
     CMAKE_ARGS += -DENGINE_ENABLE_VULKAN=ON
 else ifeq ($(UNAME_S),Darwin)

backend/cpp/audio-cpp/loaded_model.cpp

@@ -103,6 +103,9 @@ engine::core::BackendType parse_backend_type(const std::string &value) {
     if (value == "cuda") {
         return engine::core::BackendType::Cuda;
     }
+    if (value == "hip" || value == "rocm") {
+        return engine::core::BackendType::Hip;
+    }
     if (value == "vulkan") {
         return engine::core::BackendType::Vulkan;
     }
@@ -116,7 +119,7 @@ engine::core::BackendType parse_backend_type(const std::string &value) {
         return engine::core::BackendType::Cpu;
     }
     throw ConfigError("audio-cpp: unknown backend option '" + value +
-                      "'. Known backends: cpu, cuda, vulkan, metal, best");
+                      "'. Known backends: cpu, cuda, hip, rocm, vulkan, metal, best");
 }
 
 std::filesystem::path executable_directory() {

backend/cpp/audio-cpp/model_options.cpp

@@ -59,6 +59,12 @@ bool starts_with(const std::string &value, const std::string &prefix) {
            value.compare(0, prefix.size(), prefix) == 0;
 }
 
+bool is_known_backend(const std::string &value) {
+    return value == "cpu" || value == "cuda" || value == "hip" ||
+           value == "rocm" || value == "vulkan" || value == "metal" ||
+           value == "best";
+}
+
 } // namespace
 
 ParsedOptions parse_model_options(const std::vector<std::string> &entries) {
@@ -107,6 +113,12 @@ ParsedOptions parse_model_options(const std::vector<std::string> &entries) {
         } else if (key == "task") {
             parsed.options.task = value;
         } else if (key == "backend") {
+            if (!is_known_backend(value)) {
+                parsed.error = "audio-cpp: unknown backend option '" + value +
+                               "'. Known backends: cpu, cuda, hip, rocm, "
+                               "vulkan, metal, best";
+                return parsed;
+            }
             parsed.options.backend = value;
         } else if (key == "model_spec_override") {
             parsed.options.model_spec_override = value;

backend/cpp/audio-cpp/model_options.h

@@ -17,7 +17,7 @@ struct ModelOptions {
     std::string family;
     // Pins the audio.cpp task, overriding RPC-based routing. Empty means route.
     std::string task;
-    // ggml backend: cpu, cuda, vulkan, metal, best.
+    // ggml backend: cpu, cuda, hip (or rocm), vulkan, metal, best.
     std::string backend = "cpu";
     int device = 0;
     // True once a `device:` entry has been seen. 0 is both the default and a

backend/cpp/audio-cpp/model_options_test.cpp

@@ -75,6 +75,11 @@ static void test_scalar_options() {
     check(parse_model_options({"live_idle_timeout_ms:0"}).options.live_idle_timeout_ms == 0,
           "an explicit 0 turns the live idle limit off rather than reverting to "
           "the default");
+
+    check(parse_model_options({"backend:hip"}).error.empty(),
+          "HIP backend option is accepted");
+    check(parse_model_options({"backend:rocm"}).error.empty(),
+          "ROCm backend alias is accepted");
 }
 
 // Values containing colons must survive: split on the FIRST colon only.
@@ -124,6 +129,8 @@ static void test_errors() {
           "negative device is rejected");
     check(!parse_model_options({"threads:x"}).error.empty(),
           "non-numeric threads is rejected");
+    check(!parse_model_options({"backend:unknown"}).error.empty(),
+          "unknown compute backend is rejected before model loading");
 
     // Values too large for int must be rejected, not silently wrapped into a
     // negative device index that then reaches the ggml backend selector.

backend/cpp/bonsai/Makefile

@@ -1,7 +1,7 @@
 
 # Pinned to the HEAD of the `prism` branch on https://github.com/PrismML-Eng/llama.cpp.
 # Auto-bumped nightly by .github/workflows/bump_deps.yaml.
-BONSAI_VERSION?=312bb2a93ea2bf798333fa859614fbf913ecb9e2
+BONSAI_VERSION?=9ca265a57f85f2117942490f421f64a226dd9847
 LLAMA_REPO?=https://github.com/PrismML-Eng/llama.cpp
 
 CMAKE_ARGS?=
@@ -41,7 +41,6 @@ define bonsai-build
 	# and are applied by apply-patches.sh below.
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build purge
-	bash $(CURRENT_MAKEFILE_DIR)/patch-grpc-server.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/grpc-server.cpp
 	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/grpc-server.cpp
 	bash $(LLAMA_CPP_DIR)/disable-tts-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:$(1)$(RESET))
@@ -80,7 +79,6 @@ bonsai-cpu-all:
 	# and are applied by apply-patches.sh below.
 	rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/patches
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build purge
-	bash $(CURRENT_MAKEFILE_DIR)/patch-grpc-server.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/grpc-server.cpp
 	bash $(LLAMA_CPP_DIR)/disable-score-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/grpc-server.cpp
 	bash $(LLAMA_CPP_DIR)/disable-tts-task.sh $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/grpc-server.cpp
 	$(info $(GREEN)I bonsai build info:cpu-all-variants$(RESET))

backend/cpp/bonsai/patch-grpc-server.sh

@@ -1,24 +0,0 @@
-#!/bin/bash
-# Adapt the shared llama.cpp gRPC source to the older JSON API in Bonsai.
-
-set -euo pipefail
-
-if [[ $# -ne 1 ]]; then
-    echo "usage: $0 <grpc-server.cpp>" >&2
-    exit 2
-fi
-
-SRC=$1
-if [[ ! -f "$SRC" ]]; then
-    echo "grpc-server.cpp not found at $SRC" >&2
-    exit 2
-fi
-
-if grep -q 'common_json_error' "$SRC"; then
-    echo "==> patching $SRC to use the Bonsai JSON exception type"
-    awk '{ gsub(/common_json_error/, "json::parse_error"); print }' "$SRC" > "$SRC.tmp"
-    mv "$SRC.tmp" "$SRC"
-    echo "==> Bonsai JSON exception patch OK"
-else
-    echo "==> $SRC already uses a Bonsai-compatible JSON exception type, skipping"
-fi

backend/cpp/ds4/CMakeLists.txt

@@ -84,10 +84,9 @@ elseif(DS4_GPU STREQUAL "cpu")
     set(DS4_OBJS "${DS4_DIR}/ds4_cpu.o")
 endif()
 
-# Upstream splits image preprocessing, distributed inference, tensor-parallel
-# transport, the SSD expert cache, and layer placement into GPU-agnostic
-# translation units. Link them regardless of DS4_GPU.
-list(APPEND DS4_OBJS "${DS4_DIR}/ds4_image.o")
+# Upstream splits distributed inference, tensor-parallel transport, the SSD
+# expert cache, and layer placement into GPU-agnostic translation units. Link
+# them regardless of DS4_GPU.
 list(APPEND DS4_OBJS "${DS4_DIR}/ds4_distributed.o")
 list(APPEND DS4_OBJS "${DS4_DIR}/ds4_tp.o")
 list(APPEND DS4_OBJS "${DS4_DIR}/ds4_ssd.o")

backend/cpp/ds4/Makefile

@@ -1,10 +1,10 @@
 # ds4 backend Makefile.
 #
-# Upstream pin lives below as DS4_VERSION?=6289c516273979173abbc062209a81dd3706b804
+# Upstream pin lives below as DS4_VERSION?=84cc882352757baf628a1776badf7cc54d584e28
 # (.github/bump_deps.sh) can find and update it - matches the
 # llama-cpp / ik-llama-cpp / turboquant convention.
 
-DS4_VERSION?=6289c516273979173abbc062209a81dd3706b804
+DS4_VERSION?=84cc882352757baf628a1776badf7cc54d584e28
 DS4_REPO?=https://github.com/antirez/ds4
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
@@ -18,83 +18,21 @@ UNAME_S := $(shell uname -s)
 
 CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release
 
-# nvcc must be told the target architecture explicitly for a cublas build, and
-# this is not a tuning knob. Upstream's Makefile leaves CUDA_ARCH empty and its
-# `cuda` target REFUSES to build without one, offering `cuda-spark`
-# (CUDA_ARCH=sm_121) and `cuda-generic` (CUDA_ARCH=native) instead. We drive its
-# object targets directly, which bypasses that guard: nvcc then compiles with no
-# -arch at all, and the kernels run as JIT'd PTX for its default architecture.
-# On GB10 (sm_121) that silently produced corrupt inference output above a
-# ~128-token prefill batch and ~77x slower prefill (4.21 t/s vs 325.70 t/s,
-# measured on the same box with the same model). No CI runner has a GPU, so
-# `native` has nothing to enumerate there.
-#
-# Upstream's CUDA_ARCH takes a SINGLE value (see its sm_120/sm_121 special cases
-# and the `-arch=$(CUDA_ARCH)` fallback), so it cannot express the fat binary
-# these images need. NVCC_ARCH_FLAGS is overridden instead: a command-line
-# assignment wins over the `:=` in upstream's Makefile, and its NVCCFLAGS
-# expands whatever we pass.
-#
-# The architecture lists are copied from backend/go/vllm-cpp/Makefile rather
-# than invented, so the two CUDA images cover the same GPUs: amd64 datacenter +
-# consumer, and l4t/arm64 covering Orin (87), Thor (110) and GB10 (121a).
-#
-# -DDS4_CUDA_HAVE_MXF4=1 is deliberately NOT set. Upstream only defines it for
-# single-arch sm_120/sm_121 builds and guards the code with a plain #ifdef
-# rather than __CUDA_ARCH__, so it cannot be combined with older archs in one
-# fat binary. It gates an optional MXFP4 indexer fast path whose #ifndef branch
-# returns 0 and falls back to the generic path, so omitting it costs some speed
-# on GB10, not correctness. Revisit if upstream adds __CUDA_ARCH__ guards.
-#
-# An EMPTY CUDA_MAJOR_VERSION means a local developer build, not CI: fall back
-# to upstream's own `native` handling, which needs a GPU present but is what a
-# developer building on their own machine wants. Both variables are `?=` so an
-# explicit value on the command line always wins.
-UNAME_M := $(shell uname -m)
-CUDA_MAJOR_VERSION ?=
-ifeq ($(BUILD_TYPE),cublas)
-ifeq ($(CUDA_MAJOR_VERSION),13)
-ifeq ($(UNAME_M),aarch64)
-    DS4_NVCC_ARCH_FLAGS ?= -gencode arch=compute_87,code=sm_87 \
-                           -gencode arch=compute_90a,code=sm_90a \
-                           -gencode arch=compute_100a,code=sm_100a \
-                           -gencode arch=compute_110,code=sm_110 \
-                           -gencode arch=compute_121a,code=sm_121a
-else
-    DS4_NVCC_ARCH_FLAGS ?= -gencode arch=compute_80,code=sm_80 \
-                           -gencode arch=compute_86,code=sm_86 \
-                           -gencode arch=compute_89,code=sm_89 \
-                           -gencode arch=compute_90a,code=sm_90a \
-                           -gencode arch=compute_100a,code=sm_100a \
-                           -gencode arch=compute_103a,code=sm_103a \
-                           -gencode arch=compute_120a,code=sm_120a \
-                           -gencode arch=compute_121a,code=sm_121a
-endif
-    DS4_ARCH_MAKEVARS := NVCC_ARCH_FLAGS="$(DS4_NVCC_ARCH_FLAGS)"
-else ifeq ($(CUDA_MAJOR_VERSION),)
-    # Local build: let upstream resolve the host GPU.
-    DS4_ARCH_MAKEVARS := CUDA_ARCH=native
-else
-    $(error CUDA_MAJOR_VERSION=$(CUDA_MAJOR_VERSION) has no architecture list here (13 does). Leave it empty for a native build, or pass DS4_NVCC_ARCH_FLAGS explicitly.)
-endif
-endif
-
-# Upstream splits image preprocessing, distributed inference, tensor-parallel
-# transport, the SSD expert cache, and layer placement into GPU-agnostic
-# translation units. They are shared by every GPU mode, so append them
-# unconditionally below.
+# Upstream splits distributed inference, tensor-parallel transport, the SSD
+# expert cache, and layer placement into GPU-agnostic translation units. They
+# are shared by every GPU mode, so append them unconditionally below.
 ifeq ($(BUILD_TYPE),cublas)
     CMAKE_ARGS += -DDS4_GPU=cuda
-    DS4_OBJ_TARGET := ds4.o ds4_image.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o \
+    DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o \
         cuda/mmq/ds4_ggml_stubs.o cuda/mmq/ds4_mmq.o cuda/mmq/ds4_mmq_d2r.o \
         cuda/mmq/quantize.o cuda/mmq/mmid.o cuda/mmq/mmvq.o cuda/mmq/ds4_repack.o
 else ifeq ($(UNAME_S),Darwin)
     CMAKE_ARGS += -DDS4_GPU=metal
-    DS4_OBJ_TARGET := ds4.o ds4_image.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
+    DS4_OBJ_TARGET := ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
 else
     # CPU reference path (Linux only - macOS CPU path is broken by VM bug per ds4 README).
     CMAKE_ARGS += -DDS4_GPU=cpu
-    DS4_OBJ_TARGET := ds4_cpu.o ds4_image.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
+    DS4_OBJ_TARGET := ds4_cpu.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
 endif
 
 ifneq ($(NATIVE),true)
@@ -119,11 +57,11 @@ ds4:
 # the right per-platform compile flags (Objective-C/Metal on Darwin, nvcc on Linux+CUDA).
 ds4/ds4.o: ds4
 ifeq ($(BUILD_TYPE),cublas)
-	+$(MAKE) -C ds4 $(DS4_ARCH_MAKEVARS) $(DS4_OBJ_TARGET)
+	+$(MAKE) -C ds4 $(DS4_OBJ_TARGET)
 else ifeq ($(UNAME_S),Darwin)
-	+$(MAKE) -C ds4 ds4.o ds4_image.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
+	+$(MAKE) -C ds4 ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
 else
-	+$(MAKE) -C ds4 ds4_cpu.o ds4_image.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
+	+$(MAKE) -C ds4 ds4_cpu.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
 endif
 
 grpc-server: ds4/ds4.o

backend/cpp/ds4/dsml_parser.cpp

@@ -92,8 +92,7 @@ std::string json_escape(const std::string &in) {
 
 } // namespace
 
-DsmlParser::DsmlParser(bool starts_in_thinking)
-    : state_(starts_in_thinking ? State::THINK : State::TEXT) {}
+DsmlParser::DsmlParser() = default;
 
 bool DsmlParser::IsInDsmlStructural() const {
     switch (state_) {

backend/cpp/ds4/dsml_parser.h

@@ -17,9 +17,7 @@ struct ParserEvent {
 // Streaming parser. Stateless across instances; one per Predict call.
 class DsmlParser {
 public:
-    // The chat prompt may already contain the opening thinking marker, so the
-    // generated text can begin directly with reasoning bytes.
-    explicit DsmlParser(bool starts_in_thinking = false);
+    DsmlParser();
 
     // Feed a chunk of raw model-emitted text. Appends classified events to
     // `out`. May buffer the tail of `chunk` internally if it looks like a
@@ -45,7 +43,7 @@ public:
 
 private:
     enum class State { TEXT, THINK, TOOL_CALLS, INVOKE, PARAM_VALUE };
-    State state_;
+    State state_ = State::TEXT;
     std::string buf_;
     std::string current_tool_name_;
     int tool_index_ = -1;

backend/cpp/ds4/dsml_parser_test.cpp

@@ -1,133 +0,0 @@
-// SPDX-License-Identifier: MIT
-// Standalone regression tests for the DSML streaming parser.
-//
-// The repository's backend/cpp/run-unit-tests.sh harness compiles each
-// *_test.cpp as a single translation unit, so include the implementation here.
-
-#include "dsml_parser.cpp"
-
-#include <cstdio>
-#include <string>
-#include <type_traits>
-#include <vector>
-
-namespace {
-
-struct ParsedText {
-    std::string content;
-    std::string reasoning;
-};
-
-int failures = 0;
-
-void check_equal(const std::string &got, const std::string &want,
-                 const char *name) {
-    if (got == want) return;
-    std::fprintf(stderr, "FAIL %s: got \"%s\", want \"%s\"\n",
-                 name, got.c_str(), want.c_str());
-    failures++;
-}
-
-void collect_text(const std::vector<ds4cpp::ParserEvent> &events,
-                  ParsedText *parsed) {
-    for (const auto &event : events) {
-        if (event.type == ds4cpp::ParserEvent::CONTENT) {
-            parsed->content += event.text;
-        } else if (event.type == ds4cpp::ParserEvent::REASONING) {
-            parsed->reasoning += event.text;
-        }
-    }
-}
-
-ParsedText parse_chunks(ds4cpp::DsmlParser *parser,
-                        const std::vector<std::string> &chunks) {
-    ParsedText parsed;
-    for (const auto &chunk : chunks) {
-        std::vector<ds4cpp::ParserEvent> events;
-        parser->Feed(chunk, events);
-        collect_text(events, &parsed);
-    }
-    std::vector<ds4cpp::ParserEvent> events;
-    parser->Flush(events);
-    collect_text(events, &parsed);
-    return parsed;
-}
-
-template <typename Parser>
-void test_reasoning_opened_by_prompt() {
-    if constexpr (!std::is_constructible_v<Parser, bool>) {
-        std::fprintf(stderr,
-                     "FAIL reasoning_opened_by_prompt: parser cannot start in thinking state\n");
-        failures++;
-    } else {
-        Parser parser(true);
-        ParsedText parsed = parse_chunks(
-            &parser,
-            {"We need to calculate factorial recursively.</think>Here is the answer."});
-        check_equal(parsed.reasoning,
-                    "We need to calculate factorial recursively.",
-                    "reasoning_opened_by_prompt:reasoning");
-        check_equal(parsed.content, "Here is the answer.",
-                    "reasoning_opened_by_prompt:content");
-    }
-}
-
-template <typename Parser>
-Parser text_parser() {
-    if constexpr (std::is_constructible_v<Parser, bool>) {
-        return Parser(false);
-    } else {
-        return Parser();
-    }
-}
-
-void test_reasoning_disabled() {
-    auto parser = text_parser<ds4cpp::DsmlParser>();
-    ParsedText parsed = parse_chunks(&parser, {"Here is the answer."});
-    check_equal(parsed.reasoning, "", "reasoning_disabled:reasoning");
-    check_equal(parsed.content, "Here is the answer.",
-                "reasoning_disabled:content");
-}
-
-void test_explicit_think_tag() {
-    auto parser = text_parser<ds4cpp::DsmlParser>();
-    ParsedText parsed = parse_chunks(
-        &parser, {"<think>reasoning</think>answer"});
-    check_equal(parsed.reasoning, "reasoning", "explicit_think_tag:reasoning");
-    check_equal(parsed.content, "answer", "explicit_think_tag:content");
-}
-
-template <typename Parser>
-void test_split_think_close_marker() {
-    if constexpr (!std::is_constructible_v<Parser, bool>) {
-        std::fprintf(stderr,
-                     "FAIL split_think_close_marker: parser cannot start in thinking state\n");
-        failures++;
-    } else {
-        Parser parser(true);
-        ParsedText parsed = parse_chunks(
-            &parser,
-            {"We need ", "to calculate ", "factorial", "</thi", "nk>",
-             "Here is ", "the answer."});
-        check_equal(parsed.reasoning, "We need to calculate factorial",
-                    "split_think_close_marker:reasoning");
-        check_equal(parsed.content, "Here is the answer.",
-                    "split_think_close_marker:content");
-    }
-}
-
-} // namespace
-
-int main() {
-    test_reasoning_opened_by_prompt<ds4cpp::DsmlParser>();
-    test_reasoning_disabled();
-    test_explicit_think_tag();
-    test_split_think_close_marker<ds4cpp::DsmlParser>();
-
-    if (failures == 0) {
-        std::fprintf(stderr, "all dsml_parser checks passed\n");
-        return 0;
-    }
-    std::fprintf(stderr, "%d check(s) failed\n", failures);
-    return 1;
-}

backend/cpp/ds4/generation_limits.h

@@ -1,27 +0,0 @@
-// SPDX-License-Identifier: MIT
-#pragma once
-
-#include <algorithm>
-
-namespace ds4cpp {
-
-inline int EffectiveGenerationLimit(int requested, int context_size,
-                                    int session_position) {
-  const int limit = requested > 0 ? requested : 256;
-  const int room = context_size - session_position;
-  if (room <= 1) return 0;
-  return std::min(limit, room - 1);
-}
-
-inline int RemainingGenerationBudget(int effective_limit, int produced) {
-  if (effective_limit <= produced) return 0;
-  return effective_limit - produced;
-}
-
-inline int SpeculativeAcceptedCapacity(int remaining, int draft_allowance,
-                                       int buffer_capacity) {
-  if (remaining <= 0 || draft_allowance < 0 || buffer_capacity <= 0) return 0;
-  return std::min({remaining, draft_allowance + 1, buffer_capacity});
-}
-
-} // namespace ds4cpp

backend/cpp/ds4/generation_limits_test.cpp

@@ -1,92 +0,0 @@
-// SPDX-License-Identifier: MIT
-
-#include "generation_limits.h"
-
-#include <cstdio>
-
-namespace {
-
-int failures = 0;
-
-void check_equal(int got, int want, const char *name) {
-  if (got == want) return;
-  std::fprintf(stderr, "FAIL %s: got %d, want %d\n", name, got, want);
-  failures++;
-}
-
-// Mutation caught: treating omitted or negative max_tokens as unlimited instead
-// of preserving DS4's legacy 256-token default.
-void test_nonpositive_uses_legacy_default_when_space_permits() {
-  check_equal(ds4cpp::EffectiveGenerationLimit(0, 4096, 100), 256,
-              "zero max_tokens uses legacy default");
-  check_equal(ds4cpp::EffectiveGenerationLimit(-1, 4096, 100), 256,
-              "negative max_tokens uses legacy default");
-}
-
-// Mutation caught: applying the legacy default without clamping it to the
-// post-prefill context room and reserved slot.
-void test_legacy_default_is_clamped_by_context() {
-  check_equal(ds4cpp::EffectiveGenerationLimit(0, 300, 100), 199,
-              "legacy default is context-clamped");
-}
-
-// Mutation caught: allowing an explicitly large request to overrun the
-// post-prefill context boundary.
-void test_large_positive_limit_is_clamped_to_context() {
-  check_equal(ds4cpp::EffectiveGenerationLimit(32768, 32768, 100), 32667,
-              "large positive is context-clamped");
-}
-
-// Mutation caught: replacing every positive request with the legacy default
-// rather than preserving a smaller configured limit.
-void test_smaller_positive_limit_is_preserved() {
-  check_equal(ds4cpp::EffectiveGenerationLimit(64, 4096, 100), 64,
-              "smaller positive is preserved");
-}
-
-// Mutation caught: consuming the final context slot instead of reserving it as
-// required by DS4's generation loop.
-void test_no_usable_room_returns_zero() {
-  check_equal(ds4cpp::EffectiveGenerationLimit(32, 100, 99), 0,
-              "one remaining context slot is not usable");
-}
-
-// Mutation caught: sending the original generation limit to a later
-// speculative cycle instead of subtracting tokens already produced.
-void test_remaining_budget_accounts_for_produced_tokens() {
-  check_equal(ds4cpp::RemainingGenerationBudget(10, 4), 6,
-              "remaining budget subtracts produced tokens");
-  check_equal(ds4cpp::RemainingGenerationBudget(10, 12), 0,
-              "remaining budget never becomes negative");
-}
-
-// Mutation caught: giving speculative evaluation capacity beyond either the
-// output budget, the draft allowance plus its first target token, or the fixed
-// accepted-token buffer.
-void test_speculative_capacity_obeys_all_bounds() {
-  check_equal(ds4cpp::SpeculativeAcceptedCapacity(3, 8, 8), 3,
-              "capacity respects remaining output budget");
-  check_equal(ds4cpp::SpeculativeAcceptedCapacity(20, 4, 8), 5,
-              "capacity includes one target token beyond draft allowance");
-  check_equal(ds4cpp::SpeculativeAcceptedCapacity(20, 8, 6), 6,
-              "capacity respects fixed buffer");
-}
-
-} // namespace
-
-int main() {
-  test_nonpositive_uses_legacy_default_when_space_permits();
-  test_legacy_default_is_clamped_by_context();
-  test_large_positive_limit_is_clamped_to_context();
-  test_smaller_positive_limit_is_preserved();
-  test_no_usable_room_returns_zero();
-  test_remaining_budget_accounts_for_produced_tokens();
-  test_speculative_capacity_obeys_all_bounds();
-
-  if (failures == 0) {
-    std::fprintf(stderr, "all generation limit checks passed\n");
-    return 0;
-  }
-  std::fprintf(stderr, "%d check(s) failed\n", failures);
-  return 1;
-}

backend/cpp/ds4/grpc-server.cpp

@@ -10,9 +10,7 @@
 
 #include "dsml_parser.h"   // populated in Task 12
 #include "dsml_renderer.h" // populated in Task 16
-#include "generation_limits.h"
 #include "kv_cache.h"      // populated in Task 17
-#include "request_lifecycle.h"
 
 extern "C" {
 #include "ds4.h"
@@ -37,7 +35,6 @@ extern "C" {
 #include <mutex>
 #include <string>
 #include <thread>
-#include <utility>
 #include <vector>
 
 using grpc::Server;
@@ -72,21 +69,6 @@ int g_route_timeout_sec = 60;
 
 std::atomic<Server *> g_server{nullptr};
 
-static bool server_context_cancelled(void *ud) {
-    return static_cast<ServerContext *>(ud)->IsCancelled();
-}
-
-static void set_session_cancel(void *target, ds4cpp::CancelCallback callback,
-                               void *userdata) noexcept {
-    ds4_session_set_cancel(static_cast<ds4_session *>(target), callback, userdata);
-}
-
-static bool request_should_continue(ds4cpp::RequestLifecycle *request,
-                                    ServerContext *context) {
-    request->ObserveContextCancellation(context->IsCancelled());
-    return request->ShouldContinue();
-}
-
 // Parse a "key:value" option string. Returns empty when no colon.
 static std::pair<std::string, std::string> split_option(const std::string &opt) {
     auto colon = opt.find(':');
@@ -256,58 +238,37 @@ static bool apply_engine_option(ds4_engine_options *opt, const std::string &key,
 
 // When acting as a distributed coordinator, block until the worker route
 // covers all layers (ds4_session_distributed_route_ready == 1) or the timeout
-// elapses. No-op when not distributed.
+// elapses. Returns an empty string on success, or an error message to return
+// to the client. No-op when not distributed.
 //
 // Takes the g_engine_mu lock by reference and RELEASES it during each poll
 // sleep. The wait can span up to g_route_timeout_sec seconds while workers
 // connect; holding g_engine_mu the whole time would block the Status/Health
 // readiness probes (they also lock g_engine_mu), making LocalAI's loader treat
 // a still-starting worker as hung.
-struct RouteWaitResult {
-    ds4cpp::RouteWaitDecision decision;
-    std::string error;
-};
-
-static RouteWaitResult wait_route_ready(std::unique_lock<std::mutex> &lock,
-                                        ServerContext *context) {
-    if (!g_distributed) return {ds4cpp::RouteWaitDecision::Ready, ""};
+static std::string wait_route_ready(std::unique_lock<std::mutex> &lock) {
+    if (!g_distributed) return "";
     char err[256] = {0};
     const int deadline_polls = g_route_timeout_sec * 10; // 100ms per poll
     for (int i = 0; i <= deadline_polls; ++i) {
         int ready = ds4_session_distributed_route_ready(g_session, err, sizeof(err));
-        switch (ds4cpp::DecideRouteWait(ready, context->IsCancelled())) {
-        case ds4cpp::RouteWaitDecision::Ready:
-            return {ds4cpp::RouteWaitDecision::Ready, ""};
-        case ds4cpp::RouteWaitDecision::Error:
-            return {ds4cpp::RouteWaitDecision::Error,
-                    std::string("ds4 distributed route error: ") +
-                        (err[0] ? err : "unknown")};
-        case ds4cpp::RouteWaitDecision::Cancelled:
-            return {ds4cpp::RouteWaitDecision::Cancelled, ""};
-        case ds4cpp::RouteWaitDecision::Pending:
-            break;
+        if (ready == 1) return "";
+        if (ready < 0) {
+            return std::string("ds4 distributed route error: ") +
+                   (err[0] ? err : "unknown");
         }
-        if (i == deadline_polls) break;
         // Release the lock while sleeping so Status/Health and other RPCs can
         // interleave during worker startup.
         lock.unlock();
         struct timespec ts = {0, 100L * 1000L * 1000L}; // 100ms
         nanosleep(&ts, nullptr);
         lock.lock();
-        if (context->IsCancelled()) {
-            return {ds4cpp::RouteWaitDecision::Cancelled, ""};
-        }
         // A concurrent Free() may have torn down the engine while we slept.
         if (!g_engine || !g_session) {
-            return {ds4cpp::RouteWaitDecision::Error,
-                    "ds4: model unloaded while waiting for distributed route"};
+            return "ds4: model unloaded while waiting for distributed route";
         }
     }
-    if (context->IsCancelled()) {
-        return {ds4cpp::RouteWaitDecision::Cancelled, ""};
-    }
-    return {ds4cpp::RouteWaitDecision::Error,
-            "ds4 distributed route incomplete: workers not connected (layers uncovered)"};
+    return "ds4 distributed route incomplete: workers not connected (layers uncovered)";
 }
 
 static void append_token_text(ds4_engine *engine, int token, std::string &out) {
@@ -380,9 +341,9 @@ static void collect_done(void *) {}
 struct StreamCtx {
     ds4_engine *engine;
     ServerWriter<backend::Reply> *writer;
-    ds4cpp::RequestLifecycle *request;
     ds4cpp::DsmlParser parser;
     int tokens;
+    bool aborted;
     // Track which tool indices we've seen TOOL_START for, so subsequent
     // ARGS deltas can elide the redundant id/name fields.
     std::vector<bool> tool_started;
@@ -390,7 +351,7 @@ struct StreamCtx {
 
 static void stream_emit(void *ud, int token) {
     auto *s = static_cast<StreamCtx *>(ud);
-    if (!s->request->ShouldContinue()) return;
+    if (s->aborted) return;
     if (token == ds4_token_eos(s->engine)) return;
     size_t len = 0;
     const char *text = ds4_token_text(s->engine, token, &len);
@@ -440,7 +401,7 @@ static void stream_emit(void *ud, int token) {
     reply.set_message(chunk);
     reply.set_tokens(1);
     if (any_field) {
-        s->request->ObserveStreamWrite(s->writer->Write(reply));
+        if (!s->writer->Write(reply)) s->aborted = true;
     }
     s->tokens++;
 }
@@ -796,30 +757,21 @@ public:
         return GStatus::OK;
     }
 
-    GStatus Predict(ServerContext *context, const backend::PredictOptions *request,
+    GStatus Predict(ServerContext *, const backend::PredictOptions *request,
                    backend::Reply *reply) override {
         std::unique_lock<std::mutex> lock(g_engine_mu);
         if (!g_engine || !g_session) {
             return GStatus(StatusCode::FAILED_PRECONDITION, "ds4: model not loaded");
         }
         if (GStatus id = check_model_identity(request); !id.ok()) return id;
-        RouteWaitResult route = wait_route_ready(lock, context);
-        if (route.decision == ds4cpp::RouteWaitDecision::Cancelled) {
-            return GStatus(StatusCode::CANCELLED, "ds4 request cancelled");
-        }
-        if (route.decision == ds4cpp::RouteWaitDecision::Error) {
-            return GStatus(StatusCode::UNAVAILABLE, route.error);
+        if (std::string route_err = wait_route_ready(lock); !route_err.empty()) {
+            return GStatus(StatusCode::UNAVAILABLE, route_err);
         }
         ds4_tokens prompt = {};
         build_prompt(g_engine, request, &prompt);
+        int n_predict = request->tokens() > 0 ? request->tokens() : 256;
 
-        const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
-        const bool starts_in_thinking = think_enabled &&
-            request->usetokenizertemplate() && request->messages_size() > 0;
-        CollectCtx collect = {
-            g_engine, "", ds4cpp::DsmlParser(starts_in_thinking),
-            reply, 0, {}, "", ""};
-        ds4cpp::RequestLifecycle lifecycle;
+        CollectCtx collect = {g_engine, "", {}, reply, 0, {}, "", ""};
         std::string cache_key = render_prompt_text(request);
         size_t cache_hit = maybe_load_cache(cache_key);
         (void)cache_hit; // future: skip prompt prefix if hit covers full prompt
@@ -831,27 +783,15 @@ public:
         // Either way g_session advances so the disk KV cache picks up a
         // real checkpoint after the call (see maybe_save_cache below).
         char err[256] = {0};
-        int rc;
-        {
-            ds4cpp::CancelCallbackScope cancel_scope(
-                g_session, set_session_cancel, server_context_cancelled, context);
-            rc = ds4_session_sync(g_session, &prompt, err, sizeof(err));
-        }
+        int rc = ds4_session_sync(g_session, &prompt, err, sizeof(err));
         int prompt_len = prompt.len;
         ds4_tokens_free(&prompt);
-        if (rc == DS4_SESSION_SYNC_INTERRUPTED) {
-            lifecycle.ObserveContextCancellation(true);
-        }
-        const bool generation_started = rc == 0;
-        if (generation_started) {
-            const int n_predict = ds4cpp::EffectiveGenerationLimit(
-                request->tokens(), ds4_session_ctx(g_session),
-                ds4_session_pos(g_session));
+        if (rc == 0) {
             const int eos = ds4_token_eos(g_engine);
             const int draft_max = ds4_engine_mtp_draft_tokens(g_engine);
+            const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
             int produced = 0;
             while (produced < n_predict) {
-                if (!request_should_continue(&lifecycle, context)) break;
                 SampleParams sp = compute_sample_params(request, collect.parser, think_enabled);
                 int first;
                 if (sp.temperature <= 0.0f) {
@@ -866,20 +806,13 @@ public:
                 if (draft_max > 0 && sp.temperature <= 0.0f) {
                     constexpr int kAcceptedMax = 8;
                     int accepted[kAcceptedMax];
-                    const int remaining = ds4cpp::RemainingGenerationBudget(
-                        n_predict, produced);
-                    const int cap = ds4cpp::SpeculativeAcceptedCapacity(
-                        remaining, draft_max, kAcceptedMax);
+                    int cap = std::min(kAcceptedMax, draft_max + 1);
                     int n = ds4_session_eval_speculative_argmax(
-                        g_session, first, remaining, eos,
+                        g_session, first, draft_max, eos,
                         accepted, cap, err, sizeof(err));
                     if (n < 0) { rc = -1; break; }
                     bool stop = false;
                     for (int j = 0; j < n; ++j) {
-                        if (!request_should_continue(&lifecycle, context)) {
-                            stop = true;
-                            break;
-                        }
                         if (accepted[j] == eos) { stop = true; break; }
                         collect_emit(&collect, accepted[j]);
                         if (++produced >= n_predict) { stop = true; break; }
@@ -888,26 +821,12 @@ public:
                 } else {
                     collect_emit(&collect, first);
                     if (++produced >= n_predict) break;
-                    if (!request_should_continue(&lifecycle, context)) break;
                     rc = ds4_session_eval(g_session, first, err, sizeof(err));
                     if (rc != 0) break;
                 }
             }
+            collect_done(&collect);
         }
-
-        request_should_continue(&lifecycle, context);
-        ds4cpp::TerminalDecision terminal = ds4cpp::ResolveTerminalDecision(
-            rc == DS4_SESSION_SYNC_INTERRUPTED, rc != 0,
-            !lifecycle.ShouldFinalize());
-        if (!terminal.should_finalize) {
-            if (terminal.cause == ds4cpp::TerminalCause::EngineError) {
-                return GStatus(StatusCode::INTERNAL,
-                              std::string("ds4 generation failed: ") + err);
-            }
-            return GStatus(StatusCode::CANCELLED,
-                          "ds4 request cancelled");
-        }
-        if (generation_started) collect_done(&collect);
         maybe_save_cache(cache_key);
 
         // Flush any buffered parser state.
@@ -915,7 +834,7 @@ public:
         collect.parser.Flush(events);
         apply_events(&collect, events);
 
-        if (terminal.cause == ds4cpp::TerminalCause::EngineError) {
+        if (rc != 0) {
             return GStatus(StatusCode::INTERNAL,
                           std::string("ds4 generation failed: ") + err);
         }
@@ -938,30 +857,21 @@ public:
         return GStatus::OK;
     }
 
-    GStatus PredictStream(ServerContext *context, const backend::PredictOptions *request,
+    GStatus PredictStream(ServerContext *, const backend::PredictOptions *request,
                          ServerWriter<backend::Reply> *writer) override {
         std::unique_lock<std::mutex> lock(g_engine_mu);
         if (!g_engine || !g_session) {
             return GStatus(StatusCode::FAILED_PRECONDITION, "ds4: model not loaded");
         }
         if (GStatus id = check_model_identity(request); !id.ok()) return id;
-        RouteWaitResult route = wait_route_ready(lock, context);
-        if (route.decision == ds4cpp::RouteWaitDecision::Cancelled) {
-            return GStatus(StatusCode::CANCELLED, "ds4 request cancelled");
-        }
-        if (route.decision == ds4cpp::RouteWaitDecision::Error) {
-            return GStatus(StatusCode::UNAVAILABLE, route.error);
+        if (std::string route_err = wait_route_ready(lock); !route_err.empty()) {
+            return GStatus(StatusCode::UNAVAILABLE, route_err);
         }
         ds4_tokens prompt = {};
         build_prompt(g_engine, request, &prompt);
+        int n_predict = request->tokens() > 0 ? request->tokens() : 256;
 
-        const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
-        const bool starts_in_thinking = think_enabled &&
-            request->usetokenizertemplate() && request->messages_size() > 0;
-        ds4cpp::RequestLifecycle lifecycle;
-        StreamCtx s = {
-            g_engine, writer, &lifecycle,
-            ds4cpp::DsmlParser(starts_in_thinking), 0, {}};
+        StreamCtx s = {g_engine, writer, {}, 0, false, {}};
         std::string cache_key = render_prompt_text(request);
         size_t cache_hit = maybe_load_cache(cache_key);
         (void)cache_hit;
@@ -969,26 +879,14 @@ public:
         // Manual loop on g_session - see Predict() above for the rationale.
         // MTP speculative path used when ds4_engine_mtp_draft_tokens > 0.
         char err[256] = {0};
-        int rc;
-        {
-            ds4cpp::CancelCallbackScope cancel_scope(
-                g_session, set_session_cancel, server_context_cancelled, context);
-            rc = ds4_session_sync(g_session, &prompt, err, sizeof(err));
-        }
+        int rc = ds4_session_sync(g_session, &prompt, err, sizeof(err));
         ds4_tokens_free(&prompt);
-        if (rc == DS4_SESSION_SYNC_INTERRUPTED) {
-            lifecycle.ObserveContextCancellation(true);
-        }
-        const bool generation_started = rc == 0;
-        if (generation_started) {
-            const int n_predict = ds4cpp::EffectiveGenerationLimit(
-                request->tokens(), ds4_session_ctx(g_session),
-                ds4_session_pos(g_session));
+        if (rc == 0) {
             const int eos = ds4_token_eos(g_engine);
             const int draft_max = ds4_engine_mtp_draft_tokens(g_engine);
+            const bool think_enabled = ds4_think_mode_enabled(parse_think_mode(request));
             int produced = 0;
-            while (produced < n_predict) {
-                if (!request_should_continue(&lifecycle, context)) break;
+            while (produced < n_predict && !s.aborted) {
                 SampleParams sp = compute_sample_params(request, s.parser, think_enabled);
                 int first;
                 if (sp.temperature <= 0.0f) {
@@ -1002,77 +900,50 @@ public:
                 if (draft_max > 0 && sp.temperature <= 0.0f) {
                     constexpr int kAcceptedMax = 8;
                     int accepted[kAcceptedMax];
-                    const int remaining = ds4cpp::RemainingGenerationBudget(
-                        n_predict, produced);
-                    const int cap = ds4cpp::SpeculativeAcceptedCapacity(
-                        remaining, draft_max, kAcceptedMax);
+                    int cap = std::min(kAcceptedMax, draft_max + 1);
                     int n = ds4_session_eval_speculative_argmax(
-                        g_session, first, remaining, eos,
+                        g_session, first, draft_max, eos,
                         accepted, cap, err, sizeof(err));
                     if (n < 0) { rc = -1; break; }
                     bool stop = false;
                     for (int j = 0; j < n; ++j) {
-                        if (!request_should_continue(&lifecycle, context)) {
-                            stop = true;
-                            break;
-                        }
                         if (accepted[j] == eos) { stop = true; break; }
                         stream_emit(&s, accepted[j]);
-                        if (!lifecycle.ShouldContinue()) { stop = true; break; }
+                        if (s.aborted) { stop = true; break; }
                         if (++produced >= n_predict) { stop = true; break; }
                     }
                     if (stop) break;
                 } else {
                     stream_emit(&s, first);
-                    if (!lifecycle.ShouldContinue() || ++produced >= n_predict) break;
-                    if (!request_should_continue(&lifecycle, context)) break;
+                    if (s.aborted || ++produced >= n_predict) break;
                     rc = ds4_session_eval(g_session, first, err, sizeof(err));
                     if (rc != 0) break;
                 }
             }
+            stream_done(&s);
+        }
+        maybe_save_cache(cache_key);
+
+        // Flush parser state.
+        std::vector<ds4cpp::ParserEvent> events;
+        s.parser.Flush(events);
+        if (!events.empty() && !s.aborted) {
+            backend::Reply reply;
+            auto *delta = reply.add_chat_deltas();
+            for (const auto &e : events) {
+                if (e.type == ds4cpp::ParserEvent::CONTENT) {
+                    delta->set_content(delta->content() + e.text);
+                } else if (e.type == ds4cpp::ParserEvent::REASONING) {
+                    delta->set_reasoning_content(delta->reasoning_content() + e.text);
+                }
+            }
+            s.writer->Write(reply);
         }
 
-        request_should_continue(&lifecycle, context);
-        ds4cpp::TerminalDecision terminal = ds4cpp::ResolveTerminalDecision(
-            rc == DS4_SESSION_SYNC_INTERRUPTED, rc != 0,
-            !lifecycle.ShouldFinalize());
-        terminal = ds4cpp::RunPostlude(
-            terminal,
-            [&]() {
-                ds4cpp::DsmlParser staged_parser = s.parser;
-                std::vector<ds4cpp::ParserEvent> events;
-                staged_parser.Flush(events);
-                bool write_succeeded = true;
-                if (!events.empty()) {
-                    backend::Reply reply;
-                    auto *delta = reply.add_chat_deltas();
-                    for (const auto &e : events) {
-                        if (e.type == ds4cpp::ParserEvent::CONTENT) {
-                            delta->set_content(delta->content() + e.text);
-                        } else if (e.type == ds4cpp::ParserEvent::REASONING) {
-                            delta->set_reasoning_content(
-                                delta->reasoning_content() + e.text);
-                        }
-                    }
-                    write_succeeded = s.writer->Write(reply);
-                }
-                lifecycle.ObserveStreamWrite(write_succeeded);
-                request_should_continue(&lifecycle, context);
-                if (!lifecycle.ShouldFinalize()) return false;
-                s.parser = std::move(staged_parser);
-                if (generation_started) stream_done(&s);
-                return true;
-            },
-            [&]() { maybe_save_cache(cache_key); });
-
-        if (terminal.cause == ds4cpp::TerminalCause::EngineError) {
+        if (rc != 0 && !s.aborted) {
             return GStatus(StatusCode::INTERNAL,
                           std::string("ds4 generation failed: ") + err);
         }
-        if (terminal.cause == ds4cpp::TerminalCause::Cancelled) {
-            return GStatus(StatusCode::CANCELLED,
-                          "ds4 request cancelled");
-        }
         return GStatus::OK;
     }
 

backend/cpp/ds4/request_lifecycle.h

@@ -1,111 +0,0 @@
-// SPDX-License-Identifier: MIT
-#pragma once
-
-namespace ds4cpp {
-
-using CancelCallback = bool (*)(void *);
-using CancelSetter = void (*)(void *, CancelCallback, void *) noexcept;
-
-class CancelCallbackScope {
-public:
-    CancelCallbackScope(void *target, CancelSetter setter,
-                        CancelCallback callback, void *userdata) noexcept
-        : target_(target), setter_(setter) {
-        setter_(target_, callback, userdata);
-    }
-
-    ~CancelCallbackScope() noexcept {
-        setter_(target_, nullptr, nullptr);
-    }
-
-    CancelCallbackScope(const CancelCallbackScope &) = delete;
-    CancelCallbackScope &operator=(const CancelCallbackScope &) = delete;
-
-private:
-    void *target_;
-    CancelSetter setter_;
-};
-
-enum class RouteWaitDecision {
-    Pending,
-    Ready,
-    Error,
-    Cancelled,
-};
-
-inline RouteWaitDecision DecideRouteWait(int route_status, bool cancelled) {
-    if (cancelled) return RouteWaitDecision::Cancelled;
-    if (route_status > 0) return RouteWaitDecision::Ready;
-    if (route_status < 0) return RouteWaitDecision::Error;
-    return RouteWaitDecision::Pending;
-}
-
-enum class TerminalCause {
-    Success,
-    Cancelled,
-    EngineError,
-};
-
-inline TerminalCause DecideTerminalCause(bool sync_interrupted,
-                                         bool engine_error,
-                                         bool abandoned) {
-    if (sync_interrupted) return TerminalCause::Cancelled;
-    if (engine_error) return TerminalCause::EngineError;
-    if (abandoned) return TerminalCause::Cancelled;
-    return TerminalCause::Success;
-}
-
-struct TerminalDecision {
-    TerminalCause cause;
-    bool should_finalize;
-};
-
-inline TerminalDecision ResolveTerminalDecision(bool sync_interrupted,
-                                                 bool engine_error,
-                                                 bool abandoned) {
-    return {
-        DecideTerminalCause(sync_interrupted, engine_error, abandoned),
-        !sync_interrupted && !abandoned,
-    };
-}
-
-template <typename Finalize, typename Persist>
-TerminalDecision RunPostlude(TerminalDecision terminal,
-                             Finalize transactional_finalize,
-                             Persist persist) {
-    if (!terminal.should_finalize) return terminal;
-    if (!transactional_finalize()) {
-        terminal.should_finalize = false;
-        if (terminal.cause != TerminalCause::EngineError) {
-            terminal.cause = TerminalCause::Cancelled;
-        }
-        return terminal;
-    }
-    persist();
-    return terminal;
-}
-
-class RequestLifecycle {
-public:
-    void ObserveContextCancellation(bool cancelled) {
-        context_cancelled_ = context_cancelled_ || cancelled;
-    }
-
-    void ObserveStreamWrite(bool succeeded) {
-        stream_write_aborted_ = stream_write_aborted_ || !succeeded;
-    }
-
-    bool ShouldContinue() const {
-        return !context_cancelled_ && !stream_write_aborted_;
-    }
-
-    bool ShouldFinalize() const {
-        return ShouldContinue();
-    }
-
-private:
-    bool context_cancelled_ = false;
-    bool stream_write_aborted_ = false;
-};
-
-} // namespace ds4cpp

backend/cpp/ds4/request_lifecycle_test.cpp

@@ -1,414 +0,0 @@
-// SPDX-License-Identifier: MIT
-// Standalone regression tests for DS4 request cancellation policy.
-
-#include "request_lifecycle.h"
-
-#include <cstdio>
-
-namespace {
-
-int failures = 0;
-
-struct FakeCancelTarget {
-    ds4cpp::CancelCallback callback = nullptr;
-    void *userdata = nullptr;
-    int installs = 0;
-    int clears = 0;
-};
-
-struct PostludeCounts {
-    int finalize_attempts = 0;
-    int finalize_commits = 0;
-    int cache_persists = 0;
-    bool cache_followed_commit = true;
-};
-
-ds4cpp::TerminalDecision run_fake_postlude(
-        ds4cpp::TerminalDecision terminal, bool finalize_succeeds,
-        PostludeCounts *counts) {
-    return ds4cpp::RunPostlude(
-        terminal,
-        [=]() {
-            counts->finalize_attempts++;
-            if (!finalize_succeeds) return false;
-            counts->finalize_commits++;
-            return true;
-        },
-        [=]() {
-            counts->cache_followed_commit = counts->finalize_commits == 1;
-            counts->cache_persists++;
-        });
-}
-
-bool fake_cancel(void *) {
-    return false;
-}
-
-void fake_set_cancel(void *target, ds4cpp::CancelCallback callback,
-                     void *userdata) noexcept {
-    auto *fake = static_cast<FakeCancelTarget *>(target);
-    fake->callback = callback;
-    fake->userdata = userdata;
-    if (callback) {
-        fake->installs++;
-    } else {
-        fake->clears++;
-    }
-}
-
-void check(bool condition, const char *name) {
-    if (condition) return;
-    std::fprintf(stderr, "FAIL %s\n", name);
-    failures++;
-}
-
-// Production mutation caught: treating an active request as abandoned would
-// skip its parser finalization and cache save.
-void test_active_request_continues_and_finalizes() {
-    ds4cpp::RequestLifecycle request;
-
-    check(request.ShouldContinue(), "active:continue");
-    check(request.ShouldFinalize(), "active:finalize");
-}
-
-// Production mutation caught: omitting the ServerContext cancellation branch
-// would continue decoding and finalize a partial response.
-void test_context_cancellation_stops_without_finalizing() {
-    ds4cpp::RequestLifecycle request;
-
-    request.ObserveContextCancellation(true);
-
-    check(!request.ShouldContinue(), "context_cancelled:stop");
-    check(!request.ShouldFinalize(), "context_cancelled:no_finalize");
-}
-
-// Production mutation caught: ignoring ServerWriter::Write failure would keep
-// streaming and finalize a response whose client has gone away.
-void test_stream_write_abort_stops_without_finalizing() {
-    ds4cpp::RequestLifecycle request;
-
-    request.ObserveStreamWrite(false);
-
-    check(!request.ShouldContinue(), "write_abort:stop");
-    check(!request.ShouldFinalize(), "write_abort:no_finalize");
-}
-
-// Production mutation caught: combining cancellation and write failure with
-// AND would fail to stop when either signal occurs on its own.
-void test_cancellation_and_write_abort_are_independent_or_conditions() {
-    ds4cpp::RequestLifecycle cancelled;
-    cancelled.ObserveContextCancellation(true);
-    cancelled.ObserveStreamWrite(true);
-
-    ds4cpp::RequestLifecycle write_aborted;
-    write_aborted.ObserveContextCancellation(false);
-    write_aborted.ObserveStreamWrite(false);
-
-    check(!cancelled.ShouldContinue(), "or:context_only");
-    check(!write_aborted.ShouldContinue(), "or:write_only");
-}
-
-// Production mutation caught: treating an incomplete distributed route as an
-// error would return before workers have time to connect.
-void test_route_wait_pending() {
-    check(ds4cpp::DecideRouteWait(0, false) ==
-              ds4cpp::RouteWaitDecision::Pending,
-          "route_wait:pending");
-}
-
-// Production mutation caught: failing to recognize a complete route would
-// keep a ready inference request in the polling loop.
-void test_route_wait_ready() {
-    check(ds4cpp::DecideRouteWait(1, false) ==
-              ds4cpp::RouteWaitDecision::Ready,
-          "route_wait:ready");
-}
-
-// Production mutation caught: ignoring a route probe error would poll until a
-// misleading timeout instead of returning UNAVAILABLE promptly.
-void test_route_wait_error() {
-    check(ds4cpp::DecideRouteWait(-1, false) ==
-              ds4cpp::RouteWaitDecision::Error,
-          "route_wait:error");
-}
-
-// Production mutation caught: omitting cancellation from route waiting would
-// leave an abandoned request blocked until the distributed timeout.
-void test_route_wait_cancellation() {
-    check(ds4cpp::DecideRouteWait(0, true) ==
-              ds4cpp::RouteWaitDecision::Cancelled,
-          "route_wait:cancelled");
-}
-
-// Production mutation caught: checking route errors before cancellation would
-// report UNAVAILABLE for a request the client already abandoned.
-void test_route_wait_cancellation_precedes_error() {
-    check(ds4cpp::DecideRouteWait(-1, true) ==
-              ds4cpp::RouteWaitDecision::Cancelled,
-          "route_wait:cancellation_precedence");
-}
-
-// Production mutation caught: classifying a successful active request as a
-// terminal failure would suppress its normal response finalization.
-void test_terminal_success() {
-    check(ds4cpp::DecideTerminalCause(false, false, false) ==
-              ds4cpp::TerminalCause::Success,
-          "terminal:success");
-}
-
-// Production mutation caught: treating DS4's cooperative sync interruption
-// as an ordinary engine error would return INTERNAL instead of CANCELLED.
-void test_terminal_sync_interruption_is_cancelled() {
-    check(ds4cpp::DecideTerminalCause(true, true, true) ==
-              ds4cpp::TerminalCause::Cancelled,
-          "terminal:sync_interrupted");
-}
-
-// Production mutation caught: treating every nonzero engine result as client
-// abandonment would hide genuine DS4 failures behind CANCELLED.
-void test_terminal_engine_error() {
-    check(ds4cpp::DecideTerminalCause(false, true, false) ==
-              ds4cpp::TerminalCause::EngineError,
-          "terminal:engine_error");
-}
-
-// Production mutation caught: ignoring an rc==0 context cancellation would
-// finalize and cache an abandoned request.
-void test_terminal_context_abandonment() {
-    ds4cpp::RequestLifecycle request;
-    request.ObserveContextCancellation(true);
-
-    check(ds4cpp::DecideTerminalCause(
-              false, false, !request.ShouldFinalize()) ==
-              ds4cpp::TerminalCause::Cancelled,
-          "terminal:context_abandonment");
-}
-
-// Production mutation caught: ignoring an rc==0 stream write failure would
-// finalize and cache an abandoned streaming request.
-void test_terminal_write_abandonment() {
-    ds4cpp::RequestLifecycle request;
-    request.ObserveStreamWrite(false);
-
-    check(ds4cpp::DecideTerminalCause(
-              false, false, !request.ShouldFinalize()) ==
-              ds4cpp::TerminalCause::Cancelled,
-          "terminal:write_abandonment");
-}
-
-// Production mutation caught: checking late cancellation or write failure
-// before a determined ordinary DS4 error would replace INTERNAL with CANCELLED.
-void test_terminal_engine_error_precedes_late_abandonment() {
-    ds4cpp::RequestLifecycle cancelled;
-    cancelled.ObserveContextCancellation(true);
-    ds4cpp::RequestLifecycle write_aborted;
-    write_aborted.ObserveStreamWrite(false);
-
-    check(ds4cpp::DecideTerminalCause(
-              false, true, !cancelled.ShouldFinalize()) ==
-              ds4cpp::TerminalCause::EngineError,
-          "terminal:engine_error_precedes_cancellation");
-    check(ds4cpp::DecideTerminalCause(
-              false, true, !write_aborted.ShouldFinalize()) ==
-              ds4cpp::TerminalCause::EngineError,
-          "terminal:engine_error_precedes_write_abort");
-}
-
-// Production mutation caught: using status precedence alone to gate side
-// effects would finalize and persist an engine-error request abandoned later.
-void test_abandoned_engine_error_keeps_internal_without_finalizing() {
-    ds4cpp::RequestLifecycle request;
-    request.ObserveContextCancellation(true);
-
-    ds4cpp::TerminalDecision terminal = ds4cpp::ResolveTerminalDecision(
-        false, true, !request.ShouldFinalize());
-
-    check(terminal.cause == ds4cpp::TerminalCause::EngineError,
-          "terminal_decision:abandoned_engine_error_status");
-    check(!terminal.should_finalize,
-          "terminal_decision:abandoned_engine_error_no_finalize");
-}
-
-// Production mutation caught: suppressing side effects for every engine error
-// would change the existing finalization and cache behavior of active failures.
-void test_active_engine_error_still_finalizes() {
-    ds4cpp::RequestLifecycle request;
-
-    ds4cpp::TerminalDecision terminal = ds4cpp::ResolveTerminalDecision(
-        false, true, !request.ShouldFinalize());
-
-    check(terminal.cause == ds4cpp::TerminalCause::EngineError,
-          "terminal_decision:active_engine_error_status");
-    check(terminal.should_finalize,
-          "terminal_decision:active_engine_error_finalize");
-}
-
-// Production mutation caught: persisting before committed finalization would
-// cache a state whose final buffered stream reply was never completed.
-void test_postlude_active_success_commits_then_persists() {
-    PostludeCounts counts;
-
-    ds4cpp::TerminalDecision terminal = run_fake_postlude(
-        {ds4cpp::TerminalCause::Success, true}, true, &counts);
-
-    check(terminal.cause == ds4cpp::TerminalCause::Success,
-          "postlude:success_outcome");
-    check(terminal.should_finalize, "postlude:success_committed");
-    check(counts.finalize_attempts == 1, "postlude:success_attempts");
-    check(counts.finalize_commits == 1, "postlude:success_commits");
-    check(counts.cache_persists == 1, "postlude:success_cache");
-    check(counts.cache_followed_commit, "postlude:success_cache_order");
-}
-
-// Production mutation caught: starting the postlude for an already-cancelled
-// request would flush buffered parser state or persist an abandoned session.
-void test_postlude_cancellation_skips_all_side_effects() {
-    PostludeCounts counts;
-
-    ds4cpp::TerminalDecision terminal = run_fake_postlude(
-        {ds4cpp::TerminalCause::Cancelled, false}, true, &counts);
-
-    check(terminal.cause == ds4cpp::TerminalCause::Cancelled,
-          "postlude:cancelled_outcome");
-    check(counts.finalize_attempts == 0, "postlude:cancelled_attempts");
-    check(counts.finalize_commits == 0, "postlude:cancelled_commits");
-    check(counts.cache_persists == 0, "postlude:cancelled_cache");
-}
-
-// Production mutation caught: committing the live parser or cache after a
-// failed final Write would publish an abandoned streaming postlude.
-void test_postlude_finalize_failure_cancels_without_commit_or_cache() {
-    PostludeCounts counts;
-
-    ds4cpp::TerminalDecision terminal = run_fake_postlude(
-        {ds4cpp::TerminalCause::Success, true}, false, &counts);
-
-    check(terminal.cause == ds4cpp::TerminalCause::Cancelled,
-          "postlude:write_failure_outcome");
-    check(!terminal.should_finalize, "postlude:write_failure_not_committed");
-    check(counts.finalize_attempts == 1, "postlude:write_failure_attempts");
-    check(counts.finalize_commits == 0, "postlude:write_failure_commits");
-    check(counts.cache_persists == 0, "postlude:write_failure_cache");
-}
-
-// Production mutation caught: skipping the postlude for every engine error
-// would change active internal-error finalization and cache behavior.
-void test_postlude_active_engine_error_finalizes_and_persists() {
-    PostludeCounts counts;
-
-    ds4cpp::TerminalDecision terminal = run_fake_postlude(
-        {ds4cpp::TerminalCause::EngineError, true}, true, &counts);
-
-    check(terminal.cause == ds4cpp::TerminalCause::EngineError,
-          "postlude:engine_error_outcome");
-    check(counts.finalize_attempts == 1, "postlude:engine_error_attempts");
-    check(counts.finalize_commits == 1, "postlude:engine_error_commits");
-    check(counts.cache_persists == 1, "postlude:engine_error_cache");
-    check(counts.cache_followed_commit, "postlude:engine_error_cache_order");
-}
-
-// Production mutation caught: replacing every failed transactional finalize
-// with cancellation would hide an already-determined engine error.
-void test_postlude_engine_error_finalize_failure_preserves_internal() {
-    PostludeCounts counts;
-
-    ds4cpp::TerminalDecision terminal = run_fake_postlude(
-        {ds4cpp::TerminalCause::EngineError, true}, false, &counts);
-
-    check(terminal.cause == ds4cpp::TerminalCause::EngineError,
-          "postlude:engine_error_write_failure_outcome");
-    check(!terminal.should_finalize,
-          "postlude:engine_error_write_failure_not_committed");
-    check(counts.finalize_attempts == 1,
-          "postlude:engine_error_write_failure_attempts");
-    check(counts.finalize_commits == 0,
-          "postlude:engine_error_write_failure_commits");
-    check(counts.cache_persists == 0,
-          "postlude:engine_error_write_failure_cache");
-}
-
-// Production mutation caught: status precedence must not grant side-effect
-// permission to an engine-error request that was also abandoned.
-void test_postlude_abandoned_engine_error_skips_all_side_effects() {
-    PostludeCounts counts;
-
-    ds4cpp::TerminalDecision terminal = run_fake_postlude(
-        {ds4cpp::TerminalCause::EngineError, false}, true, &counts);
-
-    check(terminal.cause == ds4cpp::TerminalCause::EngineError,
-          "postlude:abandoned_engine_error_outcome");
-    check(counts.finalize_attempts == 0,
-          "postlude:abandoned_engine_error_attempts");
-    check(counts.finalize_commits == 0,
-          "postlude:abandoned_engine_error_commits");
-    check(counts.cache_persists == 0,
-          "postlude:abandoned_engine_error_cache");
-}
-
-// Production mutation caught: failing to install the request callback would
-// make DS4 prompt synchronization unable to observe client cancellation.
-void test_cancel_callback_scope_installs_callback() {
-    FakeCancelTarget target;
-    int request_context = 42;
-
-    {
-        ds4cpp::CancelCallbackScope scope(
-            &target, fake_set_cancel, fake_cancel, &request_context);
-        check(target.callback == fake_cancel, "cancel_scope:callback_installed");
-        check(target.userdata == &request_context, "cancel_scope:userdata_installed");
-        check(target.installs == 1, "cancel_scope:installed_once");
-    }
-}
-
-// Production mutation caught: failing to clear the callback at every scope
-// exit would leave DS4 pointing at a destroyed stack-owned ServerContext.
-void test_cancel_callback_scope_clears_callback() {
-    FakeCancelTarget target;
-    int request_context = 42;
-
-    {
-        ds4cpp::CancelCallbackScope scope(
-            &target, fake_set_cancel, fake_cancel, &request_context);
-    }
-
-    check(target.callback == nullptr, "cancel_scope:callback_cleared");
-    check(target.userdata == nullptr, "cancel_scope:userdata_cleared");
-    check(target.clears == 1, "cancel_scope:cleared_once");
-}
-
-} // namespace
-
-int main() {
-    test_active_request_continues_and_finalizes();
-    test_context_cancellation_stops_without_finalizing();
-    test_stream_write_abort_stops_without_finalizing();
-    test_cancellation_and_write_abort_are_independent_or_conditions();
-    test_route_wait_pending();
-    test_route_wait_ready();
-    test_route_wait_error();
-    test_route_wait_cancellation();
-    test_route_wait_cancellation_precedes_error();
-    test_terminal_success();
-    test_terminal_sync_interruption_is_cancelled();
-    test_terminal_engine_error();
-    test_terminal_context_abandonment();
-    test_terminal_write_abandonment();
-    test_terminal_engine_error_precedes_late_abandonment();
-    test_abandoned_engine_error_keeps_internal_without_finalizing();
-    test_active_engine_error_still_finalizes();
-    test_postlude_active_success_commits_then_persists();
-    test_postlude_cancellation_skips_all_side_effects();
-    test_postlude_finalize_failure_cancels_without_commit_or_cache();
-    test_postlude_active_engine_error_finalizes_and_persists();
-    test_postlude_engine_error_finalize_failure_preserves_internal();
-    test_postlude_abandoned_engine_error_skips_all_side_effects();
-    test_cancel_callback_scope_installs_callback();
-    test_cancel_callback_scope_clears_callback();
-
-    if (failures == 0) {
-        std::fprintf(stderr, "all request_lifecycle checks passed\n");
-        return 0;
-    }
-    std::fprintf(stderr, "%d check(s) failed\n", failures);
-    return 1;
-}

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=fe215a8ccdce6b844d2a3a3bbde08ae76a6284bf
+IK_LLAMA_VERSION?=8337e4cd3861406fc04e0854b1409cd1b027fbc9
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=67672dc5b76f8bc17785a19d3dc6d1463fc2902c
+LLAMA_VERSION?=d59d455fd8ea09e5a2e87ce2a9d668267ffb5ccd
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -88,12 +88,6 @@ using grpc::ServerBuilder;
 using grpc::ServerContext;
 using grpc::Status;
 
-#if LOCALAI_HAS_MTMD_INIT_OPT
-#define LOCALAI_MTMD_INIT_OPT_ARG(value) , value
-#else
-#define LOCALAI_MTMD_INIT_OPT_ARG(value)
-#endif
-
 // gRPC bearer token auth for distributed mode.
 // Reads LOCALAI_GRPC_AUTH_TOKEN from the environment. When set, rejects
 // requests without a matching "authorization: Bearer <token>" metadata header.
@@ -300,7 +294,7 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, const
             } else {
                 SRV_WRN("[TOOLS DEBUG] parse_options: Parsed tools JSON is not an array: %s\n", tools_json.dump().c_str());
             }
-        } catch (const common_json_error& e) {
+        } catch (const json::parse_error& e) {
             SRV_WRN("Failed to parse tools JSON from proto: %s\n", e.what());
             SRV_WRN("[TOOLS DEBUG] parse_options: Tools string that failed to parse: %s\n", predict->tools().c_str());
         }
@@ -330,7 +324,7 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, const
                 SRV_DBG("[TOOLS DEBUG] Received tool_choice object from Go layer: %s\n", tool_choice_json.dump().c_str());
             }
             SRV_INF("Extracted tool_choice from proto: %s\n", predict->toolchoice().c_str());
-        } catch (const common_json_error& e) {
+        } catch (const json::parse_error& e) {
             // If parsing fails, treat as string
             data["tool_choice"] = predict->toolchoice();
             SRV_INF("Extracted tool_choice as string: %s\n", predict->toolchoice().c_str());
@@ -359,7 +353,7 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, const
             // Add to data - llama.cpp server expects it as an object (map)
             data["logit_bias"] = logit_bias_json;
             SRV_INF("Using logit_bias: %s\n", predict->logitbias().c_str());
-        } catch (const common_json_error& e) {
+        } catch (const json::parse_error& e) {
             SRV_ERR("Failed to parse logit_bias JSON from proto: %s\n", e.what());
         }
     }
@@ -404,10 +398,7 @@ json parse_options(bool streaming, const backend::PredictOptions* predict, const
             });
     }
 
-    data["stop"] = json::array();
-    for (const auto & stop : predict->stopprompts()) {
-        data["stop"].push_back(stop);
-    }
+    data["stop"] = predict->stopprompts();
     // data["n_probs"] = predict->nprobs();
     //TODO: images,
 
@@ -1125,16 +1116,14 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                 try {
                     int n = std::stoi(optval_str);
                     if (n < 0) n = 0;
-#if LOCALAI_HAS_N_CPU_FFN_HELPER
-                    llm_add_n_cpu_ffn_overrides(n, LLM_FFN_EXPS_REGEX, params.speculative.draft.tensor_buft_overrides);
-#else
+                    // Keep override-name storage alive for the lifetime of the params struct
+                    // (mirrors upstream arg.cpp behavior with a function-local static).
                     static std::list<std::string> buft_overrides_draft;
                     for (int i = 0; i < n; ++i) {
                         buft_overrides_draft.push_back(llm_ffn_exps_block_regex(i));
                         params.speculative.draft.tensor_buft_overrides.push_back(
                             {buft_overrides_draft.back().c_str(), ggml_backend_cpu_buffer_type()});
                     }
-#endif
                 } catch (...) {}
             }
 
@@ -1152,16 +1141,14 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                 try {
                     int n = std::stoi(optval_str);
                     if (n < 0) n = 0;
-#if LOCALAI_HAS_N_CPU_FFN_HELPER
-                    llm_add_n_cpu_ffn_overrides(n, LLM_FFN_EXPS_REGEX, params.tensor_buft_overrides);
-#else
+                    // Keep override-name storage alive for the lifetime of the
+                    // params struct (mirrors upstream arg.cpp's function-local static).
                     static std::list<std::string> buft_overrides_main;
                     for (int i = 0; i < n; ++i) {
                         buft_overrides_main.push_back(llm_ffn_exps_block_regex(i));
                         params.tensor_buft_overrides.push_back(
                             {buft_overrides_main.back().c_str(), ggml_backend_cpu_buffer_type()});
                     }
-#endif
                 } catch (...) {}
             }
 
@@ -1808,7 +1795,7 @@ public:
                         for (int j = 0; j < request->audios_size(); j++) rin.audios.push_back(request->audios(j));
                         for (int j = 0; j < request->videos_size(); j++) rin.videos.push_back(request->videos(j));
                     }
-                    messages_json.push_back(json::parse(llama_grpc::build_reconstructed_message(rin).dump()));
+                    messages_json.push_back(llama_grpc::build_reconstructed_message(rin));
                 }
 
                 // Final safety check: Ensure no message has null content (Jinja templates require strings)
@@ -2001,7 +1988,7 @@ public:
                             if (!body_json.contains("chat_template_kwargs")) {
                                 body_json["chat_template_kwargs"] = json::object();
                             }
-                            for (auto el : ctk.items()) {
+                            for (auto& el : ctk.items()) {
                                 body_json["chat_template_kwargs"][el.key()] = el.value();
                             }
                         }
@@ -2087,27 +2074,30 @@ public:
             // If not using chat templates, extract files from image_data/audio_data fields
             // (If using chat templates, files were already extracted by oaicompat_chat_params_parse)
             if (!request->usetokenizertemplate() || request->messages_size() == 0 || ctx_server.impl->chat_params.tmpls == nullptr) {
-                if (data.contains("image_data") && data.at("image_data").is_array())
+                const auto &images_data = data.find("image_data");
+                if (images_data != data.end() && images_data->is_array())
                 {
-                    for (const auto &img : data.at("image_data"))
+                    for (const auto &img : *images_data)
                     {
                         auto decoded_data = base64_decode(img["data"].get<std::string>());
                         files.push_back(decoded_data);
                     }
                 }
 
-                if (data.contains("audio_data") && data.at("audio_data").is_array())
+                const auto &audio_data = data.find("audio_data");
+                if (audio_data != data.end() && audio_data->is_array())
                 {
-                    for (const auto &audio : data.at("audio_data"))
+                    for (const auto &audio : *audio_data)
                     {
                         auto decoded_data = base64_decode(audio["data"].get<std::string>());
                         files.push_back(decoded_data);
                     }
                 }
 
-                if (data.contains("video_data") && data.at("video_data").is_array())
+                const auto &video_data = data.find("video_data");
+                if (video_data != data.end() && video_data->is_array())
                 {
-                    for (const auto &video : data.at("video_data"))
+                    for (const auto &video : *video_data)
                     {
                         auto decoded_data = base64_decode(video["data"].get<std::string>());
                         files.push_back(decoded_data);
@@ -2121,10 +2111,10 @@ public:
             std::vector<server_tokens> inputs;
             if (has_mtmd) {
                 // multimodal
-                inputs.push_back(process_mtmd_prompt(ctx_server.impl->mctx, prompt_str, files LOCALAI_MTMD_INIT_OPT_ARG(ctx_server.impl->init_opt)));
+                inputs.push_back(process_mtmd_prompt(ctx_server.impl->mctx, prompt_str, files));
             } else {
                  // Everything else, including multimodal completions.
-                inputs = tokenize_input_prompts(ctx_server.impl->vocab, ctx_server.impl->mctx, prompt_str, true, true LOCALAI_MTMD_INIT_OPT_ARG(ctx_server.impl->init_opt));
+                inputs = tokenize_input_prompts(ctx_server.impl->vocab, ctx_server.impl->mctx, prompt_str, true, true);
             }
 
             tasks.reserve(inputs.size());
@@ -2380,7 +2370,7 @@ public:
                         for (int j = 0; j < request->audios_size(); j++) rin.audios.push_back(request->audios(j));
                         for (int j = 0; j < request->videos_size(); j++) rin.videos.push_back(request->videos(j));
                     }
-                    messages_json.push_back(json::parse(llama_grpc::build_reconstructed_message(rin).dump()));
+                    messages_json.push_back(llama_grpc::build_reconstructed_message(rin));
                 }
 
                 // Final safety check: Ensure no message has null content (Jinja templates require strings)
@@ -2573,7 +2563,7 @@ public:
                             if (!body_json.contains("chat_template_kwargs")) {
                                 body_json["chat_template_kwargs"] = json::object();
                             }
-                            for (auto el : ctk.items()) {
+                            for (auto& el : ctk.items()) {
                                 body_json["chat_template_kwargs"][el.key()] = el.value();
                             }
                         }
@@ -2659,10 +2649,11 @@ public:
             // If not using chat templates, extract files from image_data/audio_data fields
             // (If using chat templates, files were already extracted by oaicompat_chat_params_parse)
             if (!request->usetokenizertemplate() || request->messages_size() == 0 || ctx_server.impl->chat_params.tmpls == nullptr) {
-                if (data.contains("image_data") && data.at("image_data").is_array())
+                const auto &images_data = data.find("image_data");
+                if (images_data != data.end() && images_data->is_array())
                 {
-                    std::cout << "[PREDICT] Processing " << data.at("image_data").size() << " images" << std::endl;
-                    for (const auto &img : data.at("image_data"))
+                    std::cout << "[PREDICT] Processing " << images_data->size() << " images" << std::endl;
+                    for (const auto &img : *images_data)
                     {
                         std::cout << "[PREDICT] Processing image" << std::endl;
                         auto decoded_data = base64_decode(img["data"].get<std::string>());
@@ -2670,18 +2661,20 @@ public:
                     }
                 }
 
-                if (data.contains("audio_data") && data.at("audio_data").is_array())
+                const auto &audio_data = data.find("audio_data");
+                if (audio_data != data.end() && audio_data->is_array())
                 {
-                    for (const auto &audio : data.at("audio_data"))
+                    for (const auto &audio : *audio_data)
                     {
                         auto decoded_data = base64_decode(audio["data"].get<std::string>());
                         files.push_back(decoded_data);
                     }
                 }
 
-                if (data.contains("video_data") && data.at("video_data").is_array())
+                const auto &video_data = data.find("video_data");
+                if (video_data != data.end() && video_data->is_array())
                 {
-                    for (const auto &video : data.at("video_data"))
+                    for (const auto &video : *video_data)
                     {
                         auto decoded_data = base64_decode(video["data"].get<std::string>());
                         files.push_back(decoded_data);
@@ -2696,10 +2689,10 @@ public:
             std::vector<server_tokens> inputs;
             if (has_mtmd) {
                 // multimodal
-                inputs.push_back(process_mtmd_prompt(ctx_server.impl->mctx, prompt_str, files LOCALAI_MTMD_INIT_OPT_ARG(ctx_server.impl->init_opt)));
+                inputs.push_back(process_mtmd_prompt(ctx_server.impl->mctx, prompt_str, files));
             } else {
                  // Everything else, including multimodal completions.
-                inputs = tokenize_input_prompts(ctx_server.impl->vocab, ctx_server.impl->mctx, prompt_str, true, true LOCALAI_MTMD_INIT_OPT_ARG(ctx_server.impl->init_opt));
+                inputs = tokenize_input_prompts(ctx_server.impl->vocab, ctx_server.impl->mctx, prompt_str, true, true);
             }
 
             tasks.reserve(inputs.size());
@@ -2886,7 +2879,7 @@ public:
         json prompt = body.at("embeddings");
 
 
-        auto tokenized_prompts = tokenize_input_prompts(ctx_server.impl->vocab, ctx_server.impl->mctx, prompt, true, true LOCALAI_MTMD_INIT_OPT_ARG(ctx_server.impl->init_opt));
+        auto tokenized_prompts = tokenize_input_prompts(ctx_server.impl->vocab, ctx_server.impl->mctx, prompt, true, true);
         for (const auto & tokens : tokenized_prompts) {
             // this check is necessary for models that do not add BOS token to the input
             if (tokens.empty()) {
@@ -2991,7 +2984,7 @@ public:
 
             tasks.reserve(documents.size());
             for (size_t i = 0; i < documents.size(); i++) {
-                auto tmp = format_prompt_rerank(ctx_server.impl->model_tgt, ctx_server.impl->vocab, ctx_server.impl->mctx, request->query(), documents[i] LOCALAI_MTMD_INIT_OPT_ARG(ctx_server.impl->init_opt));
+                auto tmp = format_prompt_rerank(ctx_server.impl->model_tgt, ctx_server.impl->vocab, ctx_server.impl->mctx, request->query(), documents[i]);
                 server_task task = server_task(SERVER_TASK_TYPE_RERANK);
                 task.id = rd.queue_tasks.get_new_id();
                 task.index = i;
@@ -3012,7 +3005,7 @@ public:
         }
 
         // Collect responses
-        std::vector<json> responses;
+        json responses = json::array();
         for (auto & res : all_results.results) {
             GGML_ASSERT(dynamic_cast<server_task_result_rerank*>(res.get()) != nullptr);
             responses.push_back(res->to_json());
@@ -3025,7 +3018,7 @@ public:
         // Crop results by request.top_n if specified
         int top_n = request->top_n();
         if (top_n > 0 && top_n < static_cast<int>(responses.size())) {
-            responses.resize(top_n);
+            responses = json(responses.begin(), responses.begin() + top_n);
         }
         // Set usage information
         backend::Usage* usage = rerankResult->mutable_usage();
@@ -3072,7 +3065,7 @@ public:
             return grpc::Status(grpc::StatusCode::INVALID_ARGUMENT, opts.error);
         }
 
-        auto wrapper = mtmd_helper_bitmap_init_from_file(ctx_server.impl->mctx, opts.voice_path.c_str(), false LOCALAI_MTMD_INIT_OPT_ARG(ctx_server.impl->init_opt));
+        auto wrapper = mtmd_helper_bitmap_init_from_file(ctx_server.impl->mctx, opts.voice_path.c_str(), false);
         if (!wrapper.bitmap) {
             return grpc::Status(grpc::StatusCode::INVALID_ARGUMENT,
                 "failed to read speaker reference audio: " + opts.voice_path);

backend/cpp/llama-cpp/message_content.h

@@ -52,15 +52,14 @@ inline nlohmann::ordered_json normalize_message_content(const std::string& role,
 // (#7528). A multimodal user message legitimately carries a typed-part array
 // ({type:text}, {type:image_url}, ...), which must be left intact. Shared by the
 // streaming and non-streaming paths so this invariant cannot drift between them.
-template <typename Json>
-inline void normalize_template_message(Json& msg) {
+inline void normalize_template_message(nlohmann::ordered_json& msg) {
     if (!msg.contains("content")) {
         msg["content"] = ""; // templates expect the field to exist
         return;
     }
-    auto& content = msg["content"];
+    nlohmann::ordered_json& content = msg["content"];
     const std::string role = (msg.contains("role") && msg["role"].is_string())
-                                 ? msg["role"].template get<std::string>()
+                                 ? msg["role"].get<std::string>()
                                  : std::string();
     if (content.is_null()) {
         content = ""; // #7324: null would crash content[:N] slicing

backend/cpp/llama-cpp/patches/0001-add-server-task-type-score.patch

@@ -6,9 +6,10 @@ Subject: [PATCH 1/2] score-patch
 ---
  common/common.cpp               |   6 +-
  common/common.h                 |   3 +
+ tools/CMakeLists.txt            |   1 +
  tools/server/server-context.cpp | 358 +++++++++++++++++++++++++++++++-
  tools/server/server-task.h      |  47 +++++
- 4 files changed, 405 insertions(+), 9 deletions(-)
+ 5 files changed, 406 insertions(+), 9 deletions(-)
 
 diff --git a/common/common.cpp b/common/common.cpp
 index 2e3f14c..0cec0dc 100644
@@ -41,6 +42,15 @@ index 878534d..4001df2 100644
      int32_t n_sequences           =     1; // number of sequences to decode
      int32_t n_outputs_max         =     0; // max outputs in a batch (0 = n_batch)
      int32_t n_outputs_max_per_seq =     1; // max outputs per sequence
+diff --git a/tools/CMakeLists.txt b/tools/CMakeLists.txt
+index 780df32..1d2fe8f 100644
+--- a/tools/CMakeLists.txt
++++ b/tools/CMakeLists.txt
+@@ -41,3 +41,4 @@ else()
+     add_subdirectory(fit-params)
+     add_subdirectory(results)
+ endif()
++add_subdirectory(grpc-server)
 diff --git a/tools/server/server-context.cpp b/tools/server/server-context.cpp
 index 3b5f6a1..d0e18e6 100644
 --- a/tools/server/server-context.cpp

backend/cpp/llama-cpp/patches/0002-add-server-task-type-tts.patch

@@ -659,7 +659,7 @@ index 9069463fe..b7fa1e534 100644
 +        }
 +
 +        if (speaker_ref_len > 0) {
-+            auto wrapper = mtmd_helper_bitmap_init_from_buf(ctx_server.mctx, speaker_ref_data, speaker_ref_len, false, ctx_server.init_opt);
++            auto wrapper = mtmd_helper_bitmap_init_from_buf(ctx_server.mctx, speaker_ref_data, speaker_ref_len, false);
 +            if (!wrapper.bitmap) {
 +                res->error(format_error_response("failed to decode \"speaker_ref\"", ERROR_TYPE_INVALID_REQUEST));
 +                return res;

backend/cpp/llama-cpp/prepare.sh

@@ -15,30 +15,6 @@ if [ -d "patches" ]; then
     done
 fi
 
-## Apple RDMA link fixup.
-
-## ggml-rpc hands Apple's librdma to the linker with
-## target_link_options(ggml-rpc PRIVATE "LINKER:-weak_library,..."). Link options are not
-## a usage requirement of a static library, so in our BUILD_SHARED_LIBS=OFF build the flag
-## dies with libggml-rpc.a and every ibv_* symbol transport-apple.cpp reaches for comes out
-## undefined when grpc-server and ggml-rpc-server link. Re-declare the same weak link as
-## INTERFACE so it travels to whoever links the static library.
-##
-## Guarded on the marker so a second prepare.sh over the same checkout is a no-op, and on
-## GGML_RPC_RDMA_APPLE so forks that branched before the Apple RDMA transport (turboquant,
-## bonsai) are left alone.
-RPC_CMAKE=llama.cpp/ggml/src/ggml-rpc/CMakeLists.txt
-if [ -f "$RPC_CMAKE" ] && grep -q "GGML_RPC_RDMA_APPLE" "$RPC_CMAKE" && ! grep -q "LOCALAI_RDMA_IFACE" "$RPC_CMAKE"; then
-    echo "==> ggml-rpc carries the Apple RDMA transport, re-declaring its weak librdma link as INTERFACE"
-    cat >> "$RPC_CMAKE" <<'EOF'
-
-# LOCALAI_RDMA_IFACE: added by backend/cpp/llama-cpp/prepare.sh
-if (GGML_RPC_RDMA AND APPLE AND NOT BUILD_SHARED_LIBS)
-    target_link_options(ggml-rpc INTERFACE "LINKER:-weak_library,${RDMA_LIB}")
-endif()
-EOF
-fi
-
 for file in $(ls llama.cpp/tools/server/); do
     cp -rfv llama.cpp/tools/server/$file llama.cpp/tools/grpc-server/
 done
@@ -85,23 +61,11 @@ if grep -q "server_metrics metrics;" llama.cpp/tools/server/server-task.h; then
 else
     HAS_SERVER_METRICS=0
 fi
-if grep -q "mtmd_helper_init_opt" llama.cpp/tools/mtmd/mtmd-helper.h; then
-    HAS_MTMD_INIT_OPT=1
-else
-    HAS_MTMD_INIT_OPT=0
-fi
-if grep -q "llm_add_n_cpu_ffn_overrides" llama.cpp/common/common.h; then
-    HAS_N_CPU_FFN_HELPER=1
-else
-    HAS_N_CPU_FFN_HELPER=0
-fi
 cat > llama.cpp/tools/grpc-server/llama_compat.h <<EOF
 // Generated by backend/cpp/llama-cpp/prepare.sh. Do not edit.
 #pragma once
 #define LOCALAI_LEGACY_LOAD_MODE ${LEGACY_LOAD_MODE}
 #define LOCALAI_HAS_SERVER_METRICS ${HAS_SERVER_METRICS}
-#define LOCALAI_HAS_MTMD_INIT_OPT ${HAS_MTMD_INIT_OPT}
-#define LOCALAI_HAS_N_CPU_FFN_HELPER ${HAS_N_CPU_FFN_HELPER}
 EOF
 
 set +e

backend/cpp/turboquant/patch-grpc-server.sh

@@ -8,8 +8,6 @@
 #      so the grpc-server option parser skips the two references to
 #      common_params::checkpoint_min_step (the default and the option handler).
 #      That field does not exist in the fork yet; drop this once it does.
-#   3. Use nlohmann's parse_error type in JSON catch clauses because the fork
-#      predates upstream's common_json_error wrapper.
 #
 # The fork used to lag upstream on the whole common_params_speculative refactor
 # (ggml-org/llama.cpp#22397/#22838/#22964), the model_tgt rename (#22838) and
@@ -102,16 +100,4 @@ else
     echo "==> LOCALAI_TURBOQUANT_NO_CHECKPOINT_MIN_STEP define OK"
 fi
 
-# 3. The shared source follows current upstream and catches common_json_error.
-#    TurboQuant still exposes nlohmann::json directly, so its equivalent parse
-#    failures use json::parse_error instead.
-if grep -q 'common_json_error' "$SRC"; then
-    echo "==> patching $SRC to use the TurboQuant JSON exception type"
-    awk '{ gsub(/common_json_error/, "json::parse_error"); print }' "$SRC" > "$SRC.tmp"
-    mv "$SRC.tmp" "$SRC"
-    echo "==> TurboQuant JSON exception patch OK"
-else
-    echo "==> $SRC already uses a TurboQuant-compatible JSON exception type, skipping"
-fi
-
 echo "==> all patches applied"

backend/go/crispasr/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # CrispASR version (release tag)
 CRISPASR_REPO?=https://github.com/CrispStrobe/CrispASR
-CRISPASR_VERSION?=301acd87b036764973b8bfba71e0a21818036d33
+CRISPASR_VERSION?=a153b09b37c90cd55cd9336fccbdf3ba7a289596
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/go/crispasr/gocrispasr.go

@@ -615,10 +615,10 @@ func (w *CrispASR) TTSStream(req *pb.TTSRequest, results chan []byte) error {
 		return fmt.Errorf("crispasr: tempfile: %w", err)
 	}
 	dst := tmp.Name()
-	defer func() { _ = os.Remove(dst) }()
 	if err := tmp.Close(); err != nil {
 		return fmt.Errorf("crispasr: close tempfile: %w", err)
 	}
+	defer func() { _ = os.Remove(dst) }()
 
 	if err := writeWAV(dst, pcm, w.sampleRate); err != nil {
 		return err

backend/go/depth-anything-cpp/Makefile

@@ -14,7 +14,7 @@ JOBS?=$(shell nproc --ignore=1)
 # It is kept alive by the upstream tag da2-support (survives a squash-merge);
 # repoint to the master merge commit once mudler/depth-anything.cpp PR #1 lands.
 DEPTHANYTHING_REPO?=https://github.com/mudler/depth-anything.cpp.git
-DEPTHANYTHING_VERSION?=14f7461d1f704761a038ac9f50dbde8fdb7275e2
+DEPTHANYTHING_VERSION?=54abd5c0abfd1f394e01cb3c38f2e3af4daedf85
 
 ifeq ($(NATIVE),false)
 	CMAKE_ARGS+=-DGGML_NATIVE=OFF

backend/go/locate-anything-cpp/golocateanythingcpp.go

@@ -11,7 +11,6 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"runtime"
 	"unsafe"
 
 	"github.com/mudler/LocalAI/pkg/grpc/base"
@@ -110,25 +109,30 @@ func (r *LocateAnythingCpp) Detect(opts *pb.DetectOptions) (pb.DetectResponse, e
 		return pb.DetectResponse{}, fmt.Errorf("locate-anything-cpp: a text prompt is required (open-vocabulary detection)")
 	}
 
+	// Decode base64 image and write to temp file.
 	imgData, err := base64.StdEncoding.DecodeString(opts.Src)
 	if err != nil {
 		return pb.DetectResponse{}, fmt.Errorf("locate-anything-cpp: failed to decode base64 image: %w", err)
 	}
-	if len(imgData) == 0 {
-		return pb.DetectResponse{}, fmt.Errorf("locate-anything-cpp: decoded image is empty")
+
+	tmpFile, err := os.CreateTemp("", "locate-anything-*.img")
+	if err != nil {
+		return pb.DetectResponse{}, fmt.Errorf("locate-anything-cpp: failed to create temp file: %w", err)
+	}
+	defer func() { _ = os.Remove(tmpFile.Name()) }()
+
+	if _, err := tmpFile.Write(imgData); err != nil {
+		_ = tmpFile.Close()
+		return pb.DetectResponse{}, fmt.Errorf("locate-anything-cpp: failed to write temp file: %w", err)
+	}
+	if err := tmpFile.Close(); err != nil {
+		return pb.DetectResponse{}, fmt.Errorf("locate-anything-cpp: failed to close temp file: %w", err)
 	}
 
 	// mode 0 = hybrid (Parallel Box Decoding). The JSON return value is unused:
 	// structured detections are read via the accessor functions. Still must
 	// free the returned string.
-	jsonPtr := CapiLocateBuffer(
-		r.handle,
-		uintptr(unsafe.Pointer(unsafe.SliceData(imgData))),
-		uintptr(len(imgData)),
-		prompt,
-		0,
-	)
-	runtime.KeepAlive(imgData)
+	jsonPtr := CapiLocatePath(r.handle, tmpFile.Name(), prompt, 0)
 	if jsonPtr != 0 {
 		CapiFreeString(jsonPtr)
 	}

backend/go/locate-anything-cpp/golocateanythingcpp_unit_test.go

@@ -1,54 +0,0 @@
-package main
-
-import (
-	"encoding/base64"
-	"path/filepath"
-
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
-)
-
-var _ = Describe("LocateAnythingCpp detection input", func() {
-	It("detects from memory when the temporary directory is unavailable", func() {
-		originalLocateBuffer := CapiLocateBuffer
-		originalLocatePath := CapiLocatePath
-		originalGetNDetections := CapiGetNDetections
-		defer func() {
-			CapiLocateBuffer = originalLocateBuffer
-			CapiLocatePath = originalLocatePath
-			CapiGetNDetections = originalGetNDetections
-		}()
-
-		image := []byte("encoded-image")
-		var receivedData uintptr
-		var receivedLength uintptr
-		CapiLocateBuffer = func(_ uintptr, data uintptr, length uintptr, _ string, _ int32) uintptr {
-			receivedData = data
-			receivedLength = length
-			return 0
-		}
-		CapiLocatePath = func(_ uintptr, _ string, _ string, _ int32) uintptr {
-			Fail("path-based detection must not be called")
-			return 0
-		}
-		CapiGetNDetections = func(uintptr) int32 { return 0 }
-		GinkgoT().Setenv("TMPDIR", filepath.Join(GinkgoT().TempDir(), "missing"))
-
-		result, err := (&LocateAnythingCpp{handle: 1}).Detect(&pb.DetectOptions{
-			Src:    base64.StdEncoding.EncodeToString(image),
-			Prompt: "the object",
-		})
-
-		Expect(err).NotTo(HaveOccurred())
-		Expect(result.Detections).To(BeEmpty())
-		Expect(receivedData).NotTo(BeZero())
-		Expect(receivedLength).To(Equal(uintptr(len(image))))
-	})
-
-	It("rejects an empty decoded image", func() {
-		_, err := (&LocateAnythingCpp{handle: 1}).Detect(&pb.DetectOptions{Prompt: "the object"})
-
-		Expect(err).To(MatchError("locate-anything-cpp: decoded image is empty"))
-	})
-})

backend/go/nemo-speech-cpp/Makefile

@@ -12,7 +12,7 @@
 # runs 'make -C backend/go/$(BACKEND) build' and then copies package/), so it
 # has to produce the binary and the package, not just the shared libraries.
 
-NEMO_SPEECH_VERSION?=a5b6953c4a579a2bbd1c0913ad8a85c2a4d99953
+NEMO_SPEECH_VERSION?=4f9676226f667d14608487df744f375db87127f8
 NEMO_SPEECH_REPO?=https://github.com/NVIDIA/NeMo-Speech.cpp
 
 GOCMD?=go

backend/go/omnivoice-cpp/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # omnivoice.cpp version
 OMNIVOICE_REPO?=https://github.com/ServeurpersoCom/omnivoice.cpp
-OMNIVOICE_VERSION?=040c8b344d8c670ce1475194751d119b5ef82c78
+OMNIVOICE_VERSION?=4f33af825d66e6ef1cb185e87b4589cacf747291
 SO_TARGET?=libgomnivoicecpp.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/go/rfdetr-cpp/gorfdetrcpp.go

@@ -10,7 +10,6 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"runtime"
 	"strconv"
 	"unsafe"
 
@@ -103,12 +102,24 @@ func (r *RFDetrCpp) Detect(opts *pb.DetectOptions) (pb.DetectResponse, error) {
 		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: model not loaded")
 	}
 
+	// Decode base64 image and write to temp file.
 	imgData, err := base64.StdEncoding.DecodeString(opts.Src)
 	if err != nil {
 		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to decode base64 image: %w", err)
 	}
-	if len(imgData) == 0 {
-		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: decoded image is empty")
+
+	tmpFile, err := os.CreateTemp("", "rfdetr-*.img")
+	if err != nil {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to create temp file: %w", err)
+	}
+	defer func() { _ = os.Remove(tmpFile.Name()) }()
+
+	if _, err := tmpFile.Write(imgData); err != nil {
+		_ = tmpFile.Close()
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to write temp file: %w", err)
+	}
+	if err := tmpFile.Close(); err != nil {
+		return pb.DetectResponse{}, fmt.Errorf("rfdetr-cpp: failed to close temp file: %w", err)
 	}
 
 	threshold := opts.Threshold
@@ -116,18 +127,10 @@ func (r *RFDetrCpp) Detect(opts *pb.DetectOptions) (pb.DetectResponse, error) {
 		threshold = 0.5
 	}
 
-	// JSON output from the detection ABI is unused: we read structured detections via
+	// JSON output from detect_path is unused: we read structured detections via
 	// the accessor functions. Still must free the returned string.
 	var jsonPtr uintptr
-	rc := CapiDetectBuffer(
-		r.handle,
-		uintptr(unsafe.Pointer(unsafe.SliceData(imgData))),
-		uintptr(len(imgData)),
-		threshold,
-		uint32(defaultTopK),
-		&jsonPtr,
-	)
-	runtime.KeepAlive(imgData)
+	rc := CapiDetectPath(r.handle, tmpFile.Name(), threshold, uint32(defaultTopK), &jsonPtr)
 	if jsonPtr != 0 {
 		CapiFreeString(jsonPtr)
 	}

backend/go/rfdetr-cpp/gorfdetrcpp_unit_test.go

@@ -1,56 +0,0 @@
-package main
-
-import (
-	"encoding/base64"
-	"path/filepath"
-
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
-)
-
-var _ = Describe("RFDetrCpp detection input", func() {
-	It("detects from memory when the temporary directory is unavailable", func() {
-		originalDetectBuffer := CapiDetectBuffer
-		originalDetectPath := CapiDetectPath
-		originalFreeString := CapiFreeString
-		originalGetNDetections := CapiGetNDetections
-		defer func() {
-			CapiDetectBuffer = originalDetectBuffer
-			CapiDetectPath = originalDetectPath
-			CapiFreeString = originalFreeString
-			CapiGetNDetections = originalGetNDetections
-		}()
-
-		image := []byte("encoded-image")
-		var receivedData uintptr
-		var receivedLength uintptr
-		CapiDetectBuffer = func(_ uintptr, data uintptr, length uintptr, _ float32, _ uint32, _ *uintptr) int32 {
-			receivedData = data
-			receivedLength = length
-			return 0
-		}
-		CapiDetectPath = func(_ uintptr, _ string, _ float32, _ uint32, _ *uintptr) int32 {
-			Fail("path-based detection must not be called")
-			return -1
-		}
-		CapiFreeString = func(uintptr) {}
-		CapiGetNDetections = func(uintptr) int32 { return 0 }
-		GinkgoT().Setenv("TMPDIR", filepath.Join(GinkgoT().TempDir(), "missing"))
-
-		result, err := (&RFDetrCpp{handle: 1}).Detect(&pb.DetectOptions{
-			Src: base64.StdEncoding.EncodeToString(image),
-		})
-
-		Expect(err).NotTo(HaveOccurred())
-		Expect(result.Detections).To(BeEmpty())
-		Expect(receivedData).NotTo(BeZero())
-		Expect(receivedLength).To(Equal(uintptr(len(image))))
-	})
-
-	It("rejects an empty decoded image", func() {
-		_, err := (&RFDetrCpp{handle: 1}).Detect(&pb.DetectOptions{})
-
-		Expect(err).To(MatchError("rfdetr-cpp: decoded image is empty"))
-	})
-})

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=d04e8950c1ec8d30248cbe996682b3182fb1adf6
+STABLEDIFFUSION_GGML_VERSION?=97d2990807fe6d558e395f8764198d7c7e7b411c
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 
@@ -38,11 +38,8 @@ else ifeq ($(BUILD_TYPE),hipblas)
 	ROCM_PATH ?= /opt/rocm
 	export CXX=$(ROCM_HOME)/llvm/bin/clang++
 	export CC=$(ROCM_HOME)/llvm/bin/clang
-	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
-	# SD_HIPBLAS turns on ggml's HIP backend itself; GGML_HIPBLAS is the name ggml
-	# used before it was renamed to GGML_HIP, so passing it here only produced an
-	# unused-variable warning.
-	CMAKE_ARGS+=-DSD_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
+	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1200,gfx1201
+	CMAKE_ARGS+=-DSD_HIPBLAS=ON -DGGML_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
 else ifeq ($(BUILD_TYPE),vulkan)
 	CMAKE_ARGS+=-DSD_VULKAN=ON -DGGML_VULKAN=ON
 else ifeq ($(BUILD_TYPE),metal)

backend/go/stablediffusion-ggml/cpp/gosd.cpp

@@ -401,6 +401,7 @@ int load_model(const char *model, char *model_path, char* options[], int threads
     const char *params_backend_arg = "";
     const char *rpc_servers_arg = "";
     const char *max_vram_arg = "";
+    bool stream_layers = false;
 
     int n_threads = threads;
     enum sd_type_t wtype = SD_TYPE_COUNT;
@@ -509,10 +510,7 @@ int load_model(const char *model, char *model_path, char* options[], int threads
         if (!strcmp(optname, "params_backend")) params_backend_arg = strdup(optval);
         if (!strcmp(optname, "rpc_servers")) rpc_servers_arg = strdup(optval);
         if (!strcmp(optname, "max_vram")) max_vram_arg = strdup(optval);
-        if (!strcmp(optname, "stream_layers")) {
-            // Retained as a no-op for existing configurations. Upstream now
-            // selects segmented weight streaming automatically.
-        }
+        if (!strcmp(optname, "stream_layers")) stream_layers = (strcmp(optval, "true") == 0 || strcmp(optval, "1") == 0);
 
         // vae_decode_only is still accepted for backwards compatibility with
         // existing gallery configs, but upstream dropped the option (the model
@@ -652,9 +650,11 @@ int load_model(const char *model, char *model_path, char* options[], int threads
             ctx_params.rpc_servers = env_rpc_servers;
         }
     }
-    // max_vram is an optional GiB budget or per-backend spec for automatic
-    // graph-cut execution. A zero value uses the live free-VRAM budget.
+    // max_vram: GiB budget or per-backend spec for graph-cut segmented param
+    // offload ("0" = disabled, "-1" = auto). stream_layers only has effect when
+    // max_vram is set.
     if (strlen(max_vram_arg) > 0) ctx_params.max_vram = max_vram_arg;
+    ctx_params.stream_layers = stream_layers;
     ctx_params.diffusion_flash_attn = diffusion_flash_attn;
     ctx_params.tae_preview_only = tae_preview_only;
     ctx_params.diffusion_conv_direct = diffusion_conv_direct;
@@ -1144,25 +1144,17 @@ static uint8_t* load_and_resize_image(const char* path, int target_width, int ta
 // Write sd.cpp's audio buffer to a temp WAV file (IEEE float, interleaved).
 // sd_audio_t.data is planar (all channel 0 samples, then channel 1, etc.) — we
 // interleave on the fly so ffmpeg's standard wav demuxer can read it directly.
-// Returns 0 on success and fills wav_path.
+// Returns 0 on success and fills wav_path (must be at least 64 bytes).
 static int write_planar_float_wav(const sd_audio_t* a, char* wav_path, size_t wav_path_sz) {
     if (!a || !a->data || a->sample_count == 0 || a->channels == 0 || a->sample_rate == 0) {
         return -1;
     }
 
-    const char* temp_dir = getenv("TMPDIR");
-    if (!temp_dir || temp_dir[0] == '\0') {
-        temp_dir = "/tmp";
-    }
-    int path_len = snprintf(wav_path, wav_path_sz, "%s/gosd-audio-XXXXXX.wav", temp_dir);
-    if (path_len < 0 || (size_t)path_len >= wav_path_sz) {
-        fprintf(stderr, "temporary directory path is too long\n");
-        return -1;
-    }
+    snprintf(wav_path, wav_path_sz, "/tmp/gosd-audio-XXXXXX.wav");
     int fd = mkstemps(wav_path, 4);
     if (fd < 0) { perror("mkstemps wav"); return -1; }
     FILE* f = fdopen(fd, "wb");
-    if (!f) { perror("fdopen wav"); close(fd); unlink(wav_path); return -1; }
+    if (!f) { perror("fdopen wav"); close(fd); return -1; }
 
     uint64_t frames = a->sample_count;
     uint32_t channels = a->channels;
@@ -1229,7 +1221,7 @@ static int ffmpeg_mux_raw_to_mp4(sd_image_t* frames, int num_frames, int fps,
     snprintf(fps_str, sizeof(fps_str), "%d", fps);
 
     // Optional audio: write a temp WAV file if the model produced audio.
-    char wav_path[4096] = {0};
+    char wav_path[64] = {0};
     bool have_audio = false;
     if (audio && audio->data && audio->sample_count > 0 && audio->channels > 0 && audio->sample_rate > 0) {
         if (write_planar_float_wav(audio, wav_path, sizeof(wav_path)) == 0) {
@@ -1446,3 +1438,4 @@ int unload() {
     free_sd_ctx(sd_c);
     return 0;
 }
+

backend/go/vllm-cpp/Makefile

@@ -11,7 +11,7 @@ JOBS?=$(shell nproc --ignore=1 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || e
 
 # vllm.cpp version
 VLLM_CPP_REPO?=https://github.com/mudler/vllm.cpp
-VLLM_CPP_VERSION?=6bf3abb580982f4fd2e4525ef37802ee0ce28981
+VLLM_CPP_VERSION?=438305e1577768ec0f75729456a4c8b9f425e2ee
 
 # MLX GEMM provider (darwin/metal only; see the metal branch below for why).
 # Consumed as the prebuilt pip wheel: building MLX from source needs `xcrun

backend/go/vllm-cpp/govllmcpp.go

@@ -1,6 +1,6 @@
 package main
 
-// purego bindings for the vllm.cpp stable C ABI (include/vllm.h, ABI v23).
+// purego bindings for the vllm.cpp stable C ABI (include/vllm.h, ABI v21).
 //
 // The structs below are hand-mirrored PODs of the C declarations, with
 // explicit padding so the Go layout matches the C layout on linux/darwin
@@ -21,7 +21,7 @@ import (
 // the header of the VLLM_CPP_VERSION pinned in the Makefile: the build checks
 // the two against each other, because a mismatch is only caught at runtime by
 // registerLib, where it takes the backend down on every load (issue #11379).
-const abiVersion = 23
+const abiVersion = 21
 
 // The ABI's tri-state toggles (enable_prefix_caching ABI v7,
 // enable_jump_forward ABI v10) share one encoding: 0 is NOT "off", it is
@@ -83,7 +83,6 @@ type cModelParams struct {
 	LanguageModelOnly  int32   // 0 = multimodal inputs enabled (ABI v19)
 	_                  [4]byte
 	LimitMMPerPrompt   uintptr // const char* JSON; NULL = default limits (ABI v19)
-	MMProjPath         uintptr // const char*; NULL = no GGUF projector (ABI v22)
 }
 
 // cSamplingParams mirrors vllm_sampling_params (structured fields included).

backend/go/vllm-cpp/options.go

@@ -128,40 +128,9 @@ func parseOptions(opts *pb.ModelOptions) loadOptions {
 	lo := loadOptions{}
 	applyOptionsList(&lo, opts.GetOptions())
 	applyEngineArgs(&lo, opts.GetEngineArgs())
-	applyDraftModelOption(&lo, opts.GetOptions())
 	return lo
 }
 
-// applyDraftModelOption binds a managed companion snapshot after engine_args
-// has supplied the speculative document. Companion paths do not exist until
-// LocalAI materializes the artifact, so they must replace the gallery's static
-// repository reference without disturbing the method or token budget.
-func applyDraftModelOption(lo *loadOptions, options []string) {
-	if strings.TrimSpace(lo.speculativeConfig) == "" {
-		return
-	}
-	var draftModel string
-	for _, option := range options {
-		key, value, found := strings.Cut(option, ":")
-		if found && strings.TrimSpace(key) == "draft_model" {
-			draftModel = strings.TrimSpace(value)
-		}
-	}
-	if draftModel == "" {
-		return
-	}
-
-	var spec map[string]any
-	if err := json.Unmarshal([]byte(lo.speculativeConfig), &spec); err != nil {
-		return
-	}
-	spec["model"] = draftModel
-	encoded, err := json.Marshal(spec)
-	if err == nil {
-		lo.speculativeConfig = string(encoded)
-	}
-}
-
 // applyOptionsList reads the legacy free-form "key:value" list. strings.Cut
 // splits on the FIRST colon only, so a JSON object value survives intact.
 func applyOptionsList(lo *loadOptions, options []string) {

backend/go/vllm-cpp/options_test.go

@@ -1,38 +0,0 @@
-package main
-
-import (
-	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
-
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-)
-
-var _ = Describe("managed DFlash companion options", func() {
-	It("replaces only the draft model in an existing speculative configuration", func() {
-		managedPath := ".artifacts/huggingface/0123456789abcdef/snapshot"
-		lo := parseOptions(&pb.ModelOptions{
-			Options: []string{"draft_model:" + managedPath},
-			EngineArgs: `{
-				"speculative_config": {
-					"method": "dflash",
-					"model": "Mia-AiLab/Qwen3.8-27B-DFlash2-EXL3-5.0bpw",
-					"num_speculative_tokens": 7
-				}
-			}`,
-		})
-
-		Expect(lo.speculativeConfig).To(MatchJSON(`{
-			"method": "dflash",
-			"model": ".artifacts/huggingface/0123456789abcdef/snapshot",
-			"num_speculative_tokens": 7
-		}`))
-	})
-
-	It("ignores a draft companion when speculative decoding is not configured", func() {
-		lo := parseOptions(&pb.ModelOptions{
-			Options: []string{"draft_model:.artifacts/huggingface/0123456789abcdef/snapshot"},
-		})
-
-		Expect(lo.speculativeConfig).To(BeEmpty())
-	})
-})

backend/go/vllm-cpp/vllmcpp_test.go

@@ -16,7 +16,7 @@ func TestVllmCpp(t *testing.T) {
 	RunSpecs(t, "vllm-cpp suite")
 }
 
-// The Go POD mirrors must match the C struct layout of vllm.h (ABI v23)
+// The Go POD mirrors must match the C struct layout of vllm.h (ABI v21)
 // byte-for-byte: these offsets are the C offsets on LP64 (linux/darwin
 // amd64+arm64). A failure here means govllmcpp.go drifted from vllm.h.
 var _ = Describe("C ABI struct mirrors", func() {
@@ -24,7 +24,7 @@ var _ = Describe("C ABI struct mirrors", func() {
 		// VLLM_ABI_VERSION in the vllm.h of VLLM_CPP_VERSION (Makefile).
 		// Moving the pin past this without growing the mirrors below ships a
 		// backend that refuses every load at startup (issue #11379).
-		Expect(abiVersion).To(Equal(23))
+		Expect(abiVersion).To(Equal(21))
 	})
 
 	It("cModelParams matches vllm_model_params", func() {
@@ -51,8 +51,7 @@ var _ = Describe("C ABI struct mirrors", func() {
 		Expect(unsafe.Offsetof(p.KVCacheMemoryBytes)).To(Equal(uintptr(104)))
 		Expect(unsafe.Offsetof(p.LanguageModelOnly)).To(Equal(uintptr(112)))
 		Expect(unsafe.Offsetof(p.LimitMMPerPrompt)).To(Equal(uintptr(120)))
-		Expect(unsafe.Offsetof(p.MMProjPath)).To(Equal(uintptr(128)))
-		Expect(unsafe.Sizeof(p)).To(Equal(uintptr(136)))
+		Expect(unsafe.Sizeof(p)).To(Equal(uintptr(128)))
 	})
 
 	It("cSamplingParams matches vllm_sampling_params (ABI v8)", func() {

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=c44b60b8053bbf2a5c1e014f11323fb3f2485177
+WHISPER_CPP_VERSION?=4834a2327d008ace3ec5a9ed00f51454bcabbc1c
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/index.yaml

@@ -150,6 +150,7 @@
     - audio-transcription
     - CPU
     - CUDA
+    - HIP
     - Metal
   # No vulkan key: the vulkan image would carry a Vulkan loader with no Mesa ICD
   # (see the audio-cpp block in .github/backend-matrix.yml). Pointing a
@@ -161,6 +162,7 @@
     nvidia: "cuda12-audio-cpp"
     nvidia-cuda-12: "cuda12-audio-cpp"
     nvidia-cuda-13: "cuda13-audio-cpp"
+    amd: "rocm-audio-cpp"
     metal: "metal-audio-cpp"
     metal-darwin-arm64: "metal-audio-cpp"
 - &whispercpp
@@ -510,7 +512,7 @@
     default: "cpu-stablediffusion-ggml"
     nvidia: "cuda12-stablediffusion-ggml"
     intel: "intel-sycl-f16-stablediffusion-ggml"
-    amd: "rocm-stablediffusion-ggml"
+    # amd: "rocm-stablediffusion-ggml"
     vulkan: "vulkan-stablediffusion-ggml"
     nvidia-l4t: "nvidia-l4t-arm64-stablediffusion-ggml"
     metal: "metal-stablediffusion-ggml"
@@ -2101,6 +2103,7 @@
     nvidia: "cuda12-audio-cpp-development"
     nvidia-cuda-12: "cuda12-audio-cpp-development"
     nvidia-cuda-13: "cuda13-audio-cpp-development"
+    amd: "rocm-audio-cpp-development"
     metal: "metal-audio-cpp-development"
     metal-darwin-arm64: "metal-audio-cpp-development"
 - !!merge <<: *stablediffusionggml
@@ -2109,7 +2112,7 @@
     default: "cpu-stablediffusion-ggml-development"
     nvidia: "cuda12-stablediffusion-ggml-development"
     intel: "intel-sycl-f16-stablediffusion-ggml-development"
-    amd: "rocm-stablediffusion-ggml-development"
+    # amd: "rocm-stablediffusion-ggml-development"
     vulkan: "vulkan-stablediffusion-ggml-development"
     nvidia-l4t: "nvidia-l4t-arm64-stablediffusion-ggml-development"
     metal: "metal-stablediffusion-ggml-development"
@@ -3904,11 +3907,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml"
   mirrors:
     - localai/localai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml
-- !!merge <<: *stablediffusionggml
-  name: "rocm-stablediffusion-ggml"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-stablediffusion-ggml"
-  mirrors:
-    - localai/localai-backends:latest-gpu-rocm-hipblas-stablediffusion-ggml
 - !!merge <<: *stablediffusionggml
   name: "intel-sycl-f32-stablediffusion-ggml"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-stablediffusion-ggml"
@@ -3922,11 +3920,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml
-- !!merge <<: *stablediffusionggml
-  name: "rocm-stablediffusion-ggml-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-stablediffusion-ggml"
-  mirrors:
-    - localai/localai-backends:master-gpu-rocm-hipblas-stablediffusion-ggml
 - !!merge <<: *stablediffusionggml
   name: "intel-sycl-f32-stablediffusion-ggml-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-stablediffusion-ggml"
@@ -7054,6 +7047,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-audio-cpp"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-audio-cpp
+- !!merge <<: *audiocpp
+  name: "rocm-audio-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-audio-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-audio-cpp
+- !!merge <<: *audiocpp
+  name: "rocm-audio-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-audio-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-audio-cpp
 - !!merge <<: *audiocpp
   name: "metal-audio-cpp"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-audio-cpp"

backend/python/chatterbox/backend.py

@@ -19,7 +19,6 @@ import grpc
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
 from grpc_auth import get_auth_interceptors
-from temp_utils import cleanup_paths
 
 import tempfile
 
@@ -116,6 +115,11 @@ def merge_audio_files(audio_files, output_path, sample_rate):
     # Save the merged audio
     ta.save(output_path, merged_waveform, sample_rate)
     
+    # Clean up temporary files
+    for audio_file in audio_files:
+        if os.path.exists(audio_file):
+            os.remove(audio_file)
+
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
 
 # If MAX_WORKERS are specified in the environment use it, otherwise default to 1
@@ -222,20 +226,19 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 text_chunks = split_text_at_word_boundary(request.text, max_length=250)
                 print(f"Splitting text into chunks of 250 characters: {len(text_chunks)}", file=sys.stderr)
                 # Generate audio for each chunk
-                with cleanup_paths() as temp_audio_files:
-                    for i, chunk in enumerate(text_chunks):
-                        # Generate audio for this chunk
-                        wav = self.model.generate(chunk, **kwargs)
-
-                        # Register ownership before saving so a partial write is
-                        # removed too when generation or encoding fails.
-                        temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.wav')
-                        temp_file.close()
-                        temp_audio_files.append(temp_file.name)
-                        ta.save(temp_file.name, wav, self.model.sr)
-
-                    # Merge all audio files
-                    merge_audio_files(temp_audio_files, request.dst, self.model.sr)
+                temp_audio_files = []
+                for i, chunk in enumerate(text_chunks):
+                    # Generate audio for this chunk
+                    wav = self.model.generate(chunk, **kwargs)
+                    
+                    # Create temporary file for this chunk
+                    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.wav')
+                    temp_file.close()
+                    ta.save(temp_file.name, wav, self.model.sr)
+                    temp_audio_files.append(temp_file.name)
+                
+                # Merge all audio files
+                merge_audio_files(temp_audio_files, request.dst, self.model.sr)
             else:
                 # Generate audio using ChatterboxTTS for short text
                 wav = self.model.generate(request.text, **kwargs)

backend/python/common/python_utils.py

@@ -37,46 +37,6 @@ def parse_options(options_list):
     return opts
 
 
-def attach_media_parts(messages_dicts, n_images=0, n_videos=0):
-    """Rebuild the last user message as content *parts* carrying media markers.
-
-    Backends that let the tokenizer do the templating hand plain string content
-    to ``apply_chat_template``, but a chat template only emits the model's own
-    media tokens (``<|vision_start|><|image_pad|><|vision_end|>`` for the
-    Qwen-VL family, and the equivalents elsewhere) when the content is a list
-    of parts. Without those markers the engine's multimodal processor finds
-    nothing to substitute and silently discards the pixels, even though they
-    were forwarded correctly out of band.
-
-    Returns a new list whose last user message has
-    ``[{"type": "image"} * n_images, {"type": "video"} * n_videos, text]`` as
-    its content, or ``None`` when there is nothing to attach - no media, no
-    user turn, or content that is already a list of parts - so the caller can
-    keep using the original string-content list.
-    """
-    if not n_images and not n_videos:
-        return None
-    idx = next(
-        (
-            i
-            for i in reversed(range(len(messages_dicts)))
-            if messages_dicts[i].get("role") == "user"
-        ),
-        None,
-    )
-    if idx is None:
-        return None
-    text = messages_dicts[idx].get("content") or ""
-    if not isinstance(text, str):
-        return None
-    parts = [{"type": "image"}] * n_images + [{"type": "video"}] * n_videos
-    if text:
-        parts.append({"type": "text", "text": text})
-    patched = list(messages_dicts)
-    patched[idx] = dict(patched[idx], content=parts)
-    return patched
-
-
 def messages_to_dicts(proto_messages):
     """Convert proto ``Message`` objects to dicts suitable for ``apply_chat_template``.
 

backend/python/common/python_utils_test.py

@@ -14,7 +14,7 @@ import json
 import types
 import unittest
 
-from python_utils import attach_media_parts, messages_to_dicts, parse_options
+from python_utils import messages_to_dicts, parse_options
 
 
 def _msg(**fields):
@@ -118,63 +118,5 @@ class TestMessagesToDicts(unittest.TestCase):
         self.assertNotIn("tool_calls", out[0])
 
 
-class TestAttachMediaParts(unittest.TestCase):
-    def test_image_marker_added_to_last_user_turn(self):
-        messages = [
-            {"role": "system", "content": "be brief"},
-            {"role": "user", "content": "first"},
-            {"role": "assistant", "content": "ok"},
-            {"role": "user", "content": "how high is the water?"},
-        ]
-        out = attach_media_parts(messages, n_images=1)
-        self.assertEqual(
-            out[3]["content"],
-            [{"type": "image"}, {"type": "text", "text": "how high is the water?"}],
-        )
-        # Earlier turns and the input list itself are untouched.
-        self.assertEqual(out[:3], messages[:3])
-        self.assertEqual(messages[3]["content"], "how high is the water?")
-
-    def test_counts_and_order_images_then_videos(self):
-        out = attach_media_parts(
-            [{"role": "user", "content": "describe"}], n_images=2, n_videos=1
-        )
-        self.assertEqual(
-            out[0]["content"],
-            [
-                {"type": "image"},
-                {"type": "image"},
-                {"type": "video"},
-                {"type": "text", "text": "describe"},
-            ],
-        )
-
-    def test_empty_text_yields_media_only_parts(self):
-        out = attach_media_parts([{"role": "user", "content": ""}], n_images=1)
-        self.assertEqual(out[0]["content"], [{"type": "image"}])
-
-    def test_other_message_keys_are_preserved(self):
-        out = attach_media_parts(
-            [{"role": "user", "content": "hi", "name": "bob"}], n_images=1
-        )
-        self.assertEqual(out[0]["name"], "bob")
-
-    def test_no_media_is_a_no_op(self):
-        self.assertIsNone(attach_media_parts([{"role": "user", "content": "hi"}]))
-
-    def test_no_user_turn_is_a_no_op(self):
-        self.assertIsNone(
-            attach_media_parts([{"role": "system", "content": "hi"}], n_images=1)
-        )
-
-    def test_content_already_parts_is_a_no_op(self):
-        self.assertIsNone(
-            attach_media_parts(
-                [{"role": "user", "content": [{"type": "text", "text": "hi"}]}],
-                n_images=1,
-            )
-        )
-
-
 if __name__ == "__main__":
     unittest.main()

backend/python/common/temp_utils.py

@@ -1,36 +0,0 @@
-import base64
-import contextlib
-import os
-import tempfile
-
-
-@contextlib.contextmanager
-def materialize_base64(data, suffix=""):
-    """Materialize base64 data for a path-only library and always remove it."""
-    descriptor, path = tempfile.mkstemp(prefix="localai-media-", suffix=suffix)
-    try:
-        with os.fdopen(descriptor, "wb") as output:
-            descriptor = None
-            output.write(base64.b64decode(data))
-        yield path
-    finally:
-        if descriptor is not None:
-            os.close(descriptor)
-        try:
-            os.remove(path)
-        except OSError:
-            pass
-
-
-@contextlib.contextmanager
-def cleanup_paths():
-    """Collect temporary paths and remove them on success or failure."""
-    paths = []
-    try:
-        yield paths
-    finally:
-        for path in paths:
-            try:
-                os.remove(path)
-            except OSError:
-                pass

backend/python/common/temp_utils_test.py

@@ -1,41 +0,0 @@
-import os
-import tempfile
-import unittest
-from unittest import mock
-
-from temp_utils import cleanup_paths, materialize_base64
-
-
-class MaterializeBase64Test(unittest.TestCase):
-    def test_removes_materialized_file_after_success(self):
-        with tempfile.TemporaryDirectory() as directory:
-            with mock.patch.object(tempfile, "tempdir", directory):
-                with materialize_base64("aGVsbG8=", suffix=".data") as path:
-                    with open(path, "rb") as materialized:
-                        self.assertEqual(materialized.read(), b"hello")
-                self.assertFalse(os.path.exists(path))
-
-    def test_removes_materialized_file_when_consumer_fails(self):
-        with tempfile.TemporaryDirectory() as directory:
-            with mock.patch.object(tempfile, "tempdir", directory):
-                with self.assertRaisesRegex(RuntimeError, "decode failed"):
-                    with materialize_base64("aGVsbG8="):
-                        raise RuntimeError("decode failed")
-                self.assertEqual(os.listdir(directory), [])
-
-
-class CleanupPathsTest(unittest.TestCase):
-    def test_removes_every_registered_path_after_failure(self):
-        with tempfile.TemporaryDirectory() as directory:
-            paths = [os.path.join(directory, name) for name in ("one.wav", "two.wav")]
-            with self.assertRaisesRegex(RuntimeError, "merge failed"):
-                with cleanup_paths() as registered:
-                    for path in paths:
-                        open(path, "wb").close()
-                        registered.append(path)
-                    raise RuntimeError("merge failed")
-            self.assertEqual(os.listdir(directory), [])
-
-
-if __name__ == "__main__":
-    unittest.main()

backend/python/common/template/requirements-intel.txt

@@ -1,4 +1,4 @@
 --extra-index-url https://download.pytorch.org/whl/xpu
-torch==2.14.0+xpu
+torch==2.13.0+xpu
 oneccl_bind_pt==2.8.0+xpu
 optimum[openvino]

backend/python/common/template/requirements.txt

@@ -1,3 +1,3 @@
-grpcio==1.83.1
+grpcio==1.82.1
 protobuf
 grpcio-tools

backend/python/coqui/requirements.txt

@@ -1,4 +1,4 @@
-grpcio==1.83.1
+grpcio==1.83.0
 protobuf
 certifi
 packaging==26.3

backend/python/diffusers/backend.py

@@ -122,21 +122,6 @@ from diffusers.schedulers import (
     UniPCMultistepScheduler,
 )
 
-def select_device(request_cuda, device_option, cuda_available, xpu, mps_available):
-    """Pick the pipeline device. An explicit `device:` model option wins;
-    otherwise CUDA is used whenever torch reports it available (ROCm
-    builds included) or the model config forces it with `cuda: true`,
-    keeping the pre-existing XPU/MPS overrides. CPU is the fallback, not
-    the default."""
-    if device_option:
-        return device_option
-    device = "cuda" if (request_cuda or cuda_available) else "cpu"
-    if xpu:
-        device = "xpu"
-    if mps_available:
-        device = "mps"
-    return device
-
 def is_float(s):
     """Check if a string can be converted to float."""
     try:
@@ -642,13 +627,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 # modify LoraAdapter to be relative to modelFileBase
                 request.LoraAdapter = os.path.join(request.ModelPath, request.LoraAdapter)
 
-            device = select_device(
-                request.CUDA,
-                self.options.pop("device", None),
-                torch.cuda.is_available(),
-                XPU,
-                hasattr(torch.backends, "mps") and torch.backends.mps.is_available(),
-            )
+            device = "cpu" if not request.CUDA else "cuda"
+            if XPU:
+                device = "xpu"
+            mps_available = hasattr(torch.backends, "mps") and torch.backends.mps.is_available()
+            if mps_available:
+                device = "mps"
             self.device = device
             if request.LoraAdapter:
                 # Check if its a local file and not a directory ( we load lora differently for a safetensor file )
@@ -816,12 +800,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             image = image.resize((1024, 576))
 
             generator = torch.manual_seed(request.seed)
-            frames = self.pipe(image=image, guidance_scale=self.cfg_scale, decode_chunk_size=CHUNK_SIZE, generator=generator).frames[0]
+            frames = self.pipe(image, guidance_scale=self.cfg_scale, decode_chunk_size=CHUNK_SIZE, generator=generator).frames[0]
             export_to_video(frames, request.dst, fps=FPS)
             return backend_pb2.Result(message="Media generated successfully", success=True)
 
         if self.txt2vid:
-            video_frames = self.pipe(prompt=prompt, guidance_scale=self.cfg_scale, num_inference_steps=steps, num_frames=int(FRAMES)).frames
+            video_frames = self.pipe(prompt, guidance_scale=self.cfg_scale, num_inference_steps=steps, num_frames=int(FRAMES)).frames
             export_to_video(video_frames, request.dst)
             return backend_pb2.Result(message="Media generated successfully", success=True)
 
@@ -884,7 +868,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         else:
             # pass the kwargs dictionary to the self.pipe method
             image = self.pipe(
-                prompt=prompt,
+                prompt,
                 guidance_scale=self.cfg_scale,
                 **kwargs
             ).images[0]

backend/python/diffusers/test.py

@@ -7,7 +7,6 @@ import time
 from unittest.mock import patch, MagicMock
 
 # Import dynamic loader for testing (these don't need gRPC)
-import backend
 import diffusers_dynamic_loader as loader
 from diffusers import DiffusionPipeline, StableDiffusionPipeline
 
@@ -374,74 +373,3 @@ class TestGenerateImageOptionsKwargsMerge(unittest.TestCase):
         finally:
             os.unlink(src_file.name)
             os.unlink(dst_file.name)
-
-    def test_text_to_image_prompt_is_passed_by_keyword(self):
-        """Test compatibility with pipelines that take image before prompt."""
-        import os
-        import tempfile
-
-        from PIL import Image
-
-        from backend import BackendServicer
-
-        class Flux2CompatiblePipeline:
-            """Model the FLUX.2 call signature: image is before prompt."""
-
-            def __call__(self, image=None, prompt=None, **kwargs):
-                if prompt is None:
-                    raise ValueError("prompt was not passed by keyword")
-                self.prompt = prompt
-                self.kwargs = kwargs
-                return MagicMock(images=[Image.new("RGB", (4, 4))])
-
-        pipeline = Flux2CompatiblePipeline()
-        svc = BackendServicer.__new__(BackendServicer)
-        svc.pipe = pipeline
-        svc.cfg_scale = 7.5
-        svc.controlnet = None
-        svc.img2vid = False
-        svc.txt2vid = False
-        svc.clip_skip = 0
-        svc.PipelineType = "Flux2KleinPipeline"
-        svc.options = {}
-
-        with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as dst_file:
-            dst_path = dst_file.name
-
-        try:
-            request = MagicMock()
-            request.positive_prompt = "a red apple on a wooden table"
-            request.negative_prompt = ""
-            request.step = 4
-            request.seed = 0
-            request.width = 0
-            request.height = 0
-            request.src = ""
-            request.ref_images = []
-            request.dst = dst_path
-
-            svc.GenerateImage(request, context=None)
-
-            self.assertEqual(pipeline.prompt, request.positive_prompt)
-            self.assertEqual(pipeline.kwargs["num_inference_steps"], 4)
-        finally:
-            os.unlink(dst_path)
-
-
-class TestDeviceSelection(unittest.TestCase):
-    """Unit tests for backend.select_device (no GPU required)."""
-
-    def test_autodetect_cuda(self):
-        self.assertEqual(backend.select_device(False, None, True, False, False), "cuda")
-
-    def test_cpu_fallback(self):
-        self.assertEqual(backend.select_device(False, None, False, False, False), "cpu")
-
-    def test_forced_cuda(self):
-        self.assertEqual(backend.select_device(True, None, False, False, False), "cuda")
-
-    def test_device_option_wins(self):
-        self.assertEqual(backend.select_device(True, "cpu", True, True, True), "cpu")
-
-    def test_mps_overrides(self):
-        self.assertEqual(backend.select_device(False, None, True, False, True), "mps")

backend/python/longcat-video/README.md

@@ -11,7 +11,7 @@ RPC. It supports:
   systems such as NVIDIA DGX Spark.
 
 Install the `longcat-video` or `longcat-video-avatar-1.5` recipe from the
-LocalAI Model Gallery. LongCat video backend
+LocalAI Model Gallery. See the [LongCat user guide](../../../docs/content/features/longcat-video.md)
 for Studio and API examples, hardware requirements, and manual configuration.
 
 The upstream source is pinned in `Makefile` and patched at build time. The

backend/python/longcat-video/backend.py

@@ -6,7 +6,6 @@ import datetime
 import gc
 import math
 import os
-import shutil
 import signal
 import subprocess
 import sys
@@ -889,13 +888,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
     def _release_model(self):
         self.pipeline = None
         self.model_kind = None
-        try:
-            if hasattr(self, "dist") and self.dist.is_initialized():
-                self.dist.destroy_process_group()
-        finally:
-            if self._dist_store_dir is not None:
-                shutil.rmtree(self._dist_store_dir, ignore_errors=True)
-                self._dist_store_dir = None
         gc.collect()
         if hasattr(self, "torch") and self.torch.cuda.is_available():
             self.torch.cuda.empty_cache()

backend/python/qwen-asr/backend.py

@@ -18,7 +18,6 @@ sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
 from grpc_auth import get_auth_interceptors
 from model_utils import resolve_model_reference
-from device_utils import device_map_for, select_device
 
 
 
@@ -96,7 +95,13 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
 
     def LoadModel(self, request, context):
-        device = select_device(torch)
+        if torch.cuda.is_available():
+            device = "cuda"
+        else:
+            device = "cpu"
+        mps_available = hasattr(torch.backends, "mps") and torch.backends.mps.is_available()
+        if mps_available:
+            device = "mps"
         if not torch.cuda.is_available() and request.CUDA:
             return backend_pb2.Result(success=False, message="CUDA is not available")
 
@@ -118,7 +123,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         model_path, local_only = resolve_model_reference(
             request, "Qwen/Qwen3-ASR-1.7B"
         )
-        default_dtype = torch.bfloat16 if self.device in ("cuda", "xpu") else torch.float32
+        default_dtype = torch.bfloat16 if self.device == "cuda" else torch.float32
         load_dtype = default_dtype
         if "torch_dtype" in self.options:
             d = str(self.options["torch_dtype"]).lower()
@@ -140,7 +145,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         if attn_implementation is not None and isinstance(attn_implementation, str):
             attn_implementation = attn_implementation.strip() or None
 
-        device_map = device_map_for(self.device)
+        if self.device == "mps":
+            device_map = None
+        elif self.device == "cuda":
+            device_map = "cuda:0"
+        else:
+            device_map = "cpu"
 
         load_kwargs = dict(
             dtype=load_dtype,
@@ -413,4 +423,4 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Run the gRPC server.")
     parser.add_argument("--addr", default="localhost:50051", help="The address to bind the server to.")
     args = parser.parse_args()
-    serve(args.addr)
+    serve(args.addr)

backend/python/qwen-asr/device_utils.py

@@ -1,18 +0,0 @@
-def select_device(torch_module):
-    mps = getattr(getattr(torch_module, "backends", None), "mps", None)
-    if mps is not None and mps.is_available():
-        return "mps"
-    if torch_module.cuda.is_available():
-        return "cuda"
-    xpu = getattr(torch_module, "xpu", None)
-    if xpu is not None and xpu.is_available():
-        return "xpu"
-    return "cpu"
-
-
-def device_map_for(device):
-    if device == "mps":
-        return None
-    if device in ("cuda", "xpu"):
-        return f"{device}:0"
-    return "cpu"

backend/python/qwen-asr/device_utils_test.py

@@ -1,58 +0,0 @@
-import unittest
-
-from device_utils import device_map_for, select_device
-
-
-class Availability:
-    def __init__(self, available):
-        self._available = available
-
-    def is_available(self):
-        return self._available
-
-
-class TorchStub:
-    def __init__(self, *, cuda=False, mps=False, xpu=False):
-        self.cuda = Availability(cuda)
-        self.backends = type("Backends", (), {"mps": Availability(mps)})()
-        self.xpu = Availability(xpu)
-
-
-class SelectDeviceTest(unittest.TestCase):
-    def test_preserves_cuda_selection(self):
-        torch_module = TorchStub(cuda=True)
-
-        self.assertEqual(select_device(torch_module), "cuda")
-
-    def test_preserves_mps_selection(self):
-        torch_module = TorchStub(mps=True)
-
-        self.assertEqual(select_device(torch_module), "mps")
-
-    def test_selects_xpu_when_intel_gpu_is_available(self):
-        torch_module = TorchStub(xpu=True)
-
-        self.assertEqual(select_device(torch_module), "xpu")
-
-    def test_falls_back_to_cpu(self):
-        torch_module = TorchStub()
-
-        self.assertEqual(select_device(torch_module), "cpu")
-
-
-class DeviceMapTest(unittest.TestCase):
-    def test_preserves_cuda_model_placement(self):
-        self.assertEqual(device_map_for("cuda"), "cuda:0")
-
-    def test_preserves_mps_model_placement(self):
-        self.assertIsNone(device_map_for("mps"))
-
-    def test_places_the_model_on_the_first_xpu(self):
-        self.assertEqual(device_map_for("xpu"), "xpu:0")
-
-    def test_preserves_cpu_model_placement(self):
-        self.assertEqual(device_map_for("cpu"), "cpu")
-
-
-if __name__ == "__main__":
-    unittest.main()

backend/python/rerankers/requirements.txt

@@ -1,3 +1,3 @@
-grpcio==1.83.1
+grpcio==1.82.1
 protobuf
 certifi

backend/python/sglang/backend.py

@@ -40,7 +40,6 @@ import grpc
 
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
-from python_utils import attach_media_parts
 from grpc_auth import get_auth_interceptors
 from model_utils import resolve_model_reference
 
@@ -91,14 +90,6 @@ except Exception:
 
 
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
-
-# proto3 has no field presence, so an explicit 0 is indistinguishable from
-# "unset" and the zero-filter below would drop it. These two fields have a
-# meaningful zero a caller can actually intend: temperature 0 is greedy
-# decoding, and 0 is a valid seed. Silently substituting a default for either
-# turns a reproducible request into a random one.
-_EXPLICIT_ZERO_FIELDS = ("Temperature", "Seed")
-
 MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
 
 
@@ -332,7 +323,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             if not hasattr(request, proto_field):
                 continue
             value = getattr(request, proto_field)
-            if proto_field not in _EXPLICIT_ZERO_FIELDS and value in (None, 0, 0.0, [], False, ""):
+            if value in (None, 0, 0.0, [], False, ""):
                 continue
             # repeated fields come back as RepeatedScalarContainer — convert
             if hasattr(value, "__iter__") and not isinstance(value, (str, bytes)):
@@ -372,27 +363,8 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 template_kwargs["tools"] = json.loads(request.Tools)
             except json.JSONDecodeError:
                 pass
-        _thinking = request.Metadata.get("enable_thinking", "").lower()
-        if _thinking in ("true", "false"):
-            template_kwargs["enable_thinking"] = (_thinking == "true")
-
-        # sglang locates the attached images/videos by scanning the rendered
-        # prompt for the model's own media token, so the template has to be
-        # given content *parts* - string content renders a prompt with no
-        # placeholder and the media are dropped without a word (#11621).
-        media_dicts = attach_media_parts(
-            messages_dicts, len(request.Images), len(request.Videos)
-        )
-        if media_dicts is not None:
-            try:
-                return self.tokenizer.apply_chat_template(media_dicts, **template_kwargs)
-            except Exception as e:
-                # A text-only template cannot iterate content parts; fall
-                # through to the text-only prompt instead of failing.
-                print(
-                    f"chat template rejected multimodal content parts: {e!r}",
-                    file=sys.stderr,
-                )
+        if request.Metadata.get("enable_thinking", "").lower() == "true":
+            template_kwargs["enable_thinking"] = True
 
         try:
             return self.tokenizer.apply_chat_template(messages_dicts, **template_kwargs)
@@ -401,67 +373,10 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 messages_dicts, tokenize=False, add_generation_prompt=True,
             )
 
-    def _new_reasoning_parser(self, stream_reasoning: bool, prompt: str = "",
-                              grammar_constrained: bool = False):
-        """Build a ReasoningParser for one request, or None.
-
-        Reasoning templates come in two flavours. Some let the model emit the
-        opening tag, others put it into the *prompt* — Qwen3's template appends
-        ``<think>`` when thinking is on, so the completion starts straight in
-        the reasoning block and only the closing ``</think>`` ever shows up.
-        sglang's detector keys off the opening tag, so in that second case it
-        classifies the whole completion as normal content and
-        ``reasoning_content`` stays empty.
-
-        sglang's own OpenAI server covers this with
-        ``template_manager.force_reasoning``; this backend has no template
-        manager, so it derives the same signal from the rendered prompt.
-        ``force_reasoning`` is only passed when we mean True, leaving detector
-        defaults (e.g. DeepSeek-R1's built-in True) untouched.
-
-        ``grammar_constrained`` suppresses the prefill heuristic. A structured
-        decoding constraint applies from the first token, so the model cannot
-        emit the closing tag even though the template opened the block: the
-        whole completion is schema output and belongs in ``content``. Forcing
-        there files the answer as reasoning and leaves content empty. sglang's
-        own server keeps the two apart for the same reason — its grammar
-        backend owns the reasoning prefix when a reasoning parser is set.
-        """
-        if grammar_constrained:
-            prompt = ""
-
-        if not (HAS_REASONING_PARSERS and self.reasoning_parser_name):
-            return None
-
-        kwargs = {
-            "model_type": self.reasoning_parser_name,
-            "stream_reasoning": stream_reasoning,
-        }
-        try:
-            parser = ReasoningParser(**kwargs)
-        except Exception as e:
-            print(f"ReasoningParser init failed: {e!r}", file=sys.stderr)
-            return None
-
-        start = getattr(getattr(parser, "detector", None), "think_start_token", None)
-        if start and prompt and prompt.rstrip().endswith(start):
-            try:
-                parser = ReasoningParser(force_reasoning=True, **kwargs)
-            except TypeError:
-                # sglang without the force_reasoning kwarg: keep the default
-                # parser rather than failing the request.
-                pass
-            except Exception as e:
-                print(
-                    f"ReasoningParser(force_reasoning=True) failed: {e!r}",
-                    file=sys.stderr,
-                )
-
-        return parser
-
-    def _make_parsers(self, request, prompt: str = ""):
+    def _make_parsers(self, request):
         """Construct fresh per-request parser instances (stateful)."""
         tool_parser = None
+        reasoning_parser = None
 
         if HAS_TOOL_PARSERS and self.tool_parser_name and request.Tools:
             try:
@@ -473,9 +388,14 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             except Exception as e:
                 print(f"FunctionCallParser init failed: {e!r}", file=sys.stderr)
 
-        reasoning_parser = self._new_reasoning_parser(
-            True, prompt, bool(getattr(request, "Grammar", "")),
-        )
+        if HAS_REASONING_PARSERS and self.reasoning_parser_name:
+            try:
+                reasoning_parser = ReasoningParser(
+                    model_type=self.reasoning_parser_name,
+                    stream_reasoning=True,
+                )
+            except Exception as e:
+                print(f"ReasoningParser init failed: {e!r}", file=sys.stderr)
 
         return tool_parser, reasoning_parser
 
@@ -483,7 +403,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         sampling_params = self._build_sampling_params(request)
         prompt = self._build_prompt(request)
 
-        tool_parser, reasoning_parser = self._make_parsers(request, prompt)
+        tool_parser, reasoning_parser = self._make_parsers(request)
 
         image_data = list(request.Images) if request.Images else None
         video_data = list(request.Videos) if request.Videos else None
@@ -579,9 +499,15 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         final_tool_calls: List[backend_pb2.ToolCallDelta] = []
 
         if not streaming:
-            final_reasoning_parser = self._new_reasoning_parser(
-                False, prompt, bool(getattr(request, "Grammar", "")),
-            )
+            final_reasoning_parser = None
+            if HAS_REASONING_PARSERS and self.reasoning_parser_name:
+                try:
+                    final_reasoning_parser = ReasoningParser(
+                        model_type=self.reasoning_parser_name,
+                        stream_reasoning=False,
+                    )
+                except Exception:
+                    final_reasoning_parser = None
 
             if final_reasoning_parser is not None:
                 try:

backend/python/sglang/test.py

@@ -96,126 +96,6 @@ class TestSglangHelpers(unittest.TestCase):
             servicer._apply_engine_args({}, "[1,2,3]")
         self.assertIn("must be a JSON object", str(ctx.exception))
 
-    def test_build_prompt_forwards_enable_thinking(self):
-        from types import SimpleNamespace
-
-        class Tok:
-            def __init__(self):
-                self.kwargs = None
-
-            def apply_chat_template(self, messages, **kwargs):
-                self.kwargs = kwargs
-                return "PROMPT"
-
-        def kwargs_for(metadata):
-            servicer = self._servicer()
-            tok = Tok()
-            servicer.tokenizer = tok
-            msg = SimpleNamespace(
-                role="user", content="hi", name="",
-                tool_call_id="", reasoning_content="", tool_calls="",
-            )
-            req = SimpleNamespace(
-                Prompt="", UseTokenizerTemplate=True,
-                Messages=[msg], Tools="", Metadata=metadata,
-            )
-            self.assertEqual(servicer._build_prompt(req), "PROMPT")
-            return tok.kwargs
-
-        self.assertIs(kwargs_for({"enable_thinking": "true"})["enable_thinking"], True)
-        # "false" used to be dropped, so Qwen3 kept thinking on
-        self.assertIs(kwargs_for({"enable_thinking": "false"})["enable_thinking"], False)
-        self.assertNotIn("enable_thinking", kwargs_for({}))
-        self.assertIs(kwargs_for({"enable_thinking": "FALSE"})["enable_thinking"], False)
-
-    def test_reasoning_parser_forced_when_template_prefills_think_tag(self):
-        """Qwen3's template puts ``<think>`` in the prompt, so the completion
-        never contains it. Without force_reasoning the detector treats the whole
-        completion as normal text and reasoning_content stays empty."""
-        servicer = self._servicer()
-        servicer.reasoning_parser_name = "qwen3"
-
-        # What the model actually emits when the prompt ends in "<think>".
-        completion = "adding two and two</think>4"
-
-        forced = servicer._new_reasoning_parser(False, prompt="user: hi\n<think>\n")
-        reasoning, content = forced.parse_non_stream(completion)
-        self.assertEqual(reasoning, "adding two and two")
-        self.assertEqual(content, "4")
-
-        # No prefilled tag in the prompt: detector default, unchanged behaviour.
-        unforced = servicer._new_reasoning_parser(False, prompt="user: hi\n")
-        reasoning, content = unforced.parse_non_stream(completion)
-        self.assertFalse(reasoning)
-        self.assertEqual(content, completion)
-
-    def test_reasoning_parser_not_forced_when_thinking_is_off(self):
-        """Thinking off means no ``<think>`` in the prompt either, so the answer
-        must not be swallowed into reasoning_content."""
-        servicer = self._servicer()
-        servicer.reasoning_parser_name = "qwen3"
-
-        parser = servicer._new_reasoning_parser(False, prompt="user: primes?\n")
-        reasoning, content = parser.parse_non_stream("2,3,5,7,11")
-        self.assertFalse(reasoning)
-        self.assertEqual(content, "2,3,5,7,11")
-
-    def test_grammar_constrained_output_is_not_forced_into_reasoning(self):
-        """Structured decoding applies from the first token, so the model cannot
-        emit the closing tag even though the template opened the block. The whole
-        completion is schema output and must stay in content."""
-        servicer = self._servicer()
-        servicer.reasoning_parser_name = "qwen3"
-
-        schema_out = '{"findings": [{"line": 42, "issue": "off-by-one"}]}'
-        parser = servicer._new_reasoning_parser(
-            False, prompt="audit this\n<think>\n", grammar_constrained=True,
-        )
-        reasoning, content = parser.parse_non_stream(schema_out)
-        self.assertFalse(reasoning)
-        self.assertEqual(content, schema_out)
-
-    def test_reasoning_parser_absent_without_configured_parser(self):
-        servicer = self._servicer()
-        servicer.reasoning_parser_name = None
-        self.assertIsNone(servicer._new_reasoning_parser(False, prompt="<think>"))
-
-    def test_explicit_zero_temperature_and_seed_are_preserved(self):
-        """Temperature=0 is greedy decoding and 0 is a valid seed — neither is
-        an unset value. A dropped seed turns a reproducible request random."""
-        from types import SimpleNamespace
-
-        servicer = self._servicer()
-        import sys as _sys
-        _SEED_KEY_FOR_TEST = _sys.modules["backend"]._SEED_KEY
-        request = SimpleNamespace(
-            Temperature=0,
-            N=0,
-            PresencePenalty=0,
-            FrequencyPenalty=0,
-            RepetitionPenalty=0,
-            TopP=0,
-            TopK=0,
-            MinP=0,
-            Seed=0,
-            StopPrompts=[],
-            StopTokenIds=[],
-            IgnoreEOS=False,
-            Tokens=0,
-            MinTokens=0,
-            SkipSpecialTokens=False,
-            Grammar="",
-        )
-
-        params = servicer._build_sampling_params(request)
-        self.assertEqual(params["temperature"], 0)
-        self.assertEqual(params[_SEED_KEY_FOR_TEST], 0)
-        # Other protobuf-default scalar fields must remain filtered. top_k=0 in
-        # particular is not a value sglang accepts (-1 disables it), so it must
-        # keep falling through to the engine default.
-        self.assertNotIn("top_p", params)
-        self.assertNotIn("top_k", params)
-
 
 if __name__ == "__main__":
     unittest.main()

backend/python/vllm-omni/backend.py

@@ -19,6 +19,7 @@ import base64
 import io
 import json
 import gc
+import tempfile
 
 from PIL import Image
 import torch
@@ -33,7 +34,6 @@ sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
 from grpc_auth import get_auth_interceptors
 from model_utils import resolve_model_reference
-from temp_utils import materialize_base64
 from vllm_utils import parse_options, messages_to_dicts, setup_parsers
 
 
@@ -118,8 +118,13 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             return video_to_ndarrays(video_path, num_frames=16)
         # Try base64 decode
         try:
-            with materialize_base64(video_path, suffix=".data") as path:
-                return VideoAsset(name=path).np_ndarrays
+            timestamp = str(int(time.time() * 1000))
+            p = os.path.join(tempfile.gettempdir(), f"vl-{timestamp}.data")
+            with open(p, "wb") as f:
+                f.write(base64.b64decode(video_path))
+            video = VideoAsset(name=p).np_ndarrays
+            os.remove(p)
+            return video
         except:
             return None
 
@@ -131,9 +136,15 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             return (audio_signal.astype(np.float32), sr)
         # Try base64 decode
         try:
-            with materialize_base64(audio_path, suffix=".wav") as path:
-                audio_signal, sr = librosa.load(path, sr=16000)
-                return (audio_signal.astype(np.float32), sr)
+            audio_data = base64.b64decode(audio_path)
+            # Save to temp file and load
+            timestamp = str(int(time.time() * 1000))
+            p = os.path.join(tempfile.gettempdir(), f"audio-{timestamp}.wav")
+            with open(p, "wb") as f:
+                f.write(audio_data)
+            audio_signal, sr = librosa.load(p, sr=16000)
+            os.remove(p)
+            return (audio_signal.astype(np.float32), sr)
         except:
             return None
 

backend/python/vllm/backend.py

@@ -10,6 +10,7 @@ import os
 import json
 import time
 import gc
+import tempfile
 from typing import List
 from PIL import Image
 
@@ -19,10 +20,8 @@ import backend_pb2_grpc
 import grpc
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
-from python_utils import attach_media_parts
 from grpc_auth import get_auth_interceptors
 from model_utils import resolve_model_reference
-from temp_utils import materialize_base64
 from vllm_utils import apply_options_to_engine_args, normalize_option_key
 
 from vllm.engine.arg_utils import AsyncEngineArgs
@@ -61,12 +60,6 @@ except ImportError:
 
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
 
-# proto3 has no field presence, so an explicit 0 is indistinguishable from
-# "unset". These two fields have a meaningful zero a caller can intend:
-# temperature 0 is greedy decoding, and 0 is a valid seed.
-_EXPLICIT_ZERO_FIELDS = ("Temperature", "Seed")
-
-
 # If MAX_WORKERS are specified in the environment use it, otherwise default to 1
 MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
 
@@ -530,7 +523,9 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             context.set_details(str(e))
             return backend_pb2.ScoreResponse()
 
-    def _build_sampling_params(self, request):
+    async def _predict(self, request, context, streaming=False):
+        # Build the sampling parameters
+        # NOTE: this must stay in sync with the vllm backend
         request_to_sampling_params = {
             "N": "n",
             "PresencePenalty": "presence_penalty",
@@ -560,84 +555,9 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         for request_field, param_field in request_to_sampling_params.items():
             if hasattr(request, request_field):
                 value = getattr(request, request_field)
-                # See _EXPLICIT_ZERO_FIELDS: temperature 0 is greedy decoding
-                # and 0 is a valid seed, so neither may be filtered out.
-                if request_field in _EXPLICIT_ZERO_FIELDS or value not in (None, 0, [], False):
+                if value not in (None, 0, [], False):
                     setattr(sampling_params, param_field, value)
 
-        return sampling_params
-
-    def _new_reasoning_parser(self, chat_template_kwargs):
-        """Build the reasoning parser, telling it whether thinking is on.
-
-        vLLM's newer parser engines decide their *initial state* from
-        ``chat_template_kwargs``: ``Qwen3Parser`` reads
-        ``chat_template_kwargs["enable_thinking"]`` and defaults to ``True``,
-        starting in the REASONING state. Constructed without it, a completion
-        produced with thinking disabled is classified as reasoning end to end,
-        and the answer is reported in both ``reasoning_content`` and
-        ``content``.
-
-        vLLM's own OpenAI server forwards the request's chat template kwargs
-        here; this backend renders the template itself, so it forwards the
-        same dict. Older parsers do not accept the argument — fall back to the
-        plain constructor for those.
-        """
-        try:
-            return self.reasoning_parser_cls(
-                self.tokenizer, chat_template_kwargs=chat_template_kwargs or {},
-            )
-        except TypeError:
-            return self.reasoning_parser_cls(self.tokenizer)
-
-    @staticmethod
-    def _split_reasoning(rp, generated_text, prompt, reasoning, content):
-        """Decide what the reasoning parser's output actually means.
-
-        Covers the *older* parser shape, which has no initial state to set:
-        ``BaseThinkingReasoningParser.extract_reasoning`` documents its own
-        fallback — "For models that may not generate start token, assume the
-        reasoning content is always at the start." When no end token is
-        present it returns *everything* as reasoning and ``None`` as content,
-        which is right for a truncated reasoning run and wrong for a
-        completion that never contained reasoning at all.
-
-        Taking ``None`` content to mean "keep the raw text" then duplicates
-        the answer into both fields.
-
-        The prompt says which case it is. A template with thinking on leaves
-        the reasoning block open (the prompt ends with the start token); with
-        thinking off it closes the block in the prompt, so the completion is
-        plain content. Parsers that expose no token pair (the engine-based
-        adapters, which take the ``chat_template_kwargs`` route above) keep
-        the parser's verdict unchanged.
-        """
-        start = getattr(rp, "start_token", None)
-        end = getattr(rp, "end_token", None)
-
-        if end and end in generated_text:
-            # The parser split on the end token. Empty content here means the
-            # model stopped right after it, not that parsing failed.
-            return reasoning or "", content or ""
-
-        if not start:
-            # Unknown token layout — keep the previous behaviour rather than
-            # guess.
-            return reasoning or "", content if content is not None else generated_text
-
-        if not (start in generated_text or (prompt or "").rstrip().endswith(start)):
-            # No end token and the block was never open: the "reasoning starts
-            # at the beginning" fallback does not apply to this completion.
-            return "", generated_text
-
-        # Block was open and the end token never arrived — reasoning ran out of
-        # budget. It is all reasoning, and there is no answer to report.
-        return reasoning or "", content or ""
-
-    async def _predict(self, request, context, streaming=False):
-        # Build the sampling parameters
-        sampling_params = self._build_sampling_params(request)
-
         # Structured-output decoding: use Grammar field to pass JSON schema or BNF
         if HAS_GUIDED_DECODING and request.Grammar:
             try:
@@ -648,9 +568,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
         # Extract image paths and process images
         prompt = request.Prompt
-        # Kept in scope: the reasoning parser needs to know which chat
-        # template kwargs produced this prompt.
-        template_kwargs = {}
 
         image_paths = request.Images
         image_data = [self.load_image(img_path) for img_path in image_paths]
@@ -661,7 +578,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         # If tokenizer template is enabled and messages are provided instead of prompt, apply the tokenizer template
         if not request.Prompt and request.UseTokenizerTemplate and request.Messages:
             messages_dicts = self._messages_to_dicts(request.Messages)
-            template_kwargs.update({"tokenize": False, "add_generation_prompt": True})
+            template_kwargs = {"tokenize": False, "add_generation_prompt": True}
 
             # Pass tools for tool calling
             if request.Tools:
@@ -670,37 +587,17 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 except json.JSONDecodeError:
                     pass
 
-            _thinking = request.Metadata.get("enable_thinking", "").lower()
-            if _thinking in ("true", "false"):
-                template_kwargs["enable_thinking"] = (_thinking == "true")
+            # Enable thinking mode if requested
+            if request.Metadata.get("enable_thinking", "").lower() == "true":
+                template_kwargs["enable_thinking"] = True
 
-            # vLLM substitutes multi_modal_data into the model's own media
-            # token, so the template has to be given content *parts* - string
-            # content renders a prompt with no placeholder and the media are
-            # dropped without a word (#11621).
-            prompt = None
-            media_dicts = attach_media_parts(
-                messages_dicts, len(image_data), len(video_data)
-            )
-            if media_dicts is not None:
-                try:
-                    prompt = self.tokenizer.apply_chat_template(media_dicts, **template_kwargs)
-                except Exception as e:
-                    # A text-only template cannot iterate content parts; fall
-                    # through to the text-only prompt instead of failing.
-                    print(
-                        f"chat template rejected multimodal content parts: {e!r}",
-                        file=sys.stderr,
-                    )
-
-            if prompt is None:
-                try:
-                    prompt = self.tokenizer.apply_chat_template(messages_dicts, **template_kwargs)
-                except TypeError:
-                    # Some tokenizers don't support tools/enable_thinking kwargs — retry without them
-                    prompt = self.tokenizer.apply_chat_template(
-                        messages_dicts, tokenize=False, add_generation_prompt=True
-                    )
+            try:
+                prompt = self.tokenizer.apply_chat_template(messages_dicts, **template_kwargs)
+            except TypeError:
+                # Some tokenizers don't support tools/enable_thinking kwargs — retry without them
+                prompt = self.tokenizer.apply_chat_template(
+                    messages_dicts, tokenize=False, add_generation_prompt=True
+                )
 
         # Generate text using the LLM engine
         request_id = random_uuid()
@@ -856,11 +753,10 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
         if self.reasoning_parser_cls:
             try:
-                rp = self._new_reasoning_parser(template_kwargs)
+                rp = self.reasoning_parser_cls(self.tokenizer)
                 r, c = rp.extract_reasoning(generated_text, request=None)
-                reasoning_content, content = self._split_reasoning(
-                    rp, generated_text, prompt, r, c,
-                )
+                reasoning_content = r or ""
+                content = c if c is not None else generated_text
             except Exception as e:
                 print(f"Reasoning parser error: {e}", file=sys.stderr)
 
@@ -1005,8 +901,13 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             Video: The loaded video.
         """
         try:
-            with materialize_base64(video_path, suffix=".data") as path:
-                return VideoAsset(name=path).np_ndarrays
+            timestamp = str(int(time.time() * 1000))  # Generate timestamp
+            p = os.path.join(tempfile.gettempdir(), f"vl-{timestamp}.data")
+            with open(p, "wb") as f:
+                f.write(base64.b64decode(video_path))
+            video = VideoAsset(name=p).np_ndarrays
+            os.remove(p)
+            return video
         except Exception as e:
             print(f"Error loading video {video_path}: {e}", file=sys.stderr)
             return None

backend/python/vllm/install.sh

@@ -119,18 +119,14 @@ if [ "$(uname -s)" = "Darwin" ]; then
     # can rewrite it. Darwin therefore follows vllm-metal and can lag the Linux
     # vllm pin (requirements-cublas13-after.txt, bumped independently against
     # vllm/vllm) until vllm-metal supports a newer vLLM.
-    VLLM_METAL_VERSION="v0.28.0"
+    VLLM_METAL_VERSION="v0.3.0.dev20260818075955"
 
     # The coupled vLLM source version is whatever this vllm-metal release builds
-    # against. Derive it from the PINNED tag rather than hardcoding a second value
-    # that could drift. The tag is immutable, so this stays reproducible across
-    # rebuilds. Since vllm-metal 0.28 the coupling is declared in
-    # .github/vllm-release-tag.commit; older releases pinned it inline in their
-    # own install.sh, so fall back to that. The extractor reads both forms.
-    _vllm_metal_raw="https://raw.githubusercontent.com/vllm-project/vllm-metal/${VLLM_METAL_VERSION}"
-    VLLM_VERSION=$( { curl -fsSL "${_vllm_metal_raw}/.github/vllm-release-tag.commit" \
-        || curl -fsSL "${_vllm_metal_raw}/install.sh"; } \
-        | "$backend_dir/../../../scripts/lib/extract-vllm-metal-version.sh" || true)
+    # against. Derive it from
+    # the PINNED tag rather than hardcoding a second value that could drift. The
+    # tag is immutable, so this stays reproducible across rebuilds.
+    VLLM_VERSION=$(curl -fsSL "https://raw.githubusercontent.com/vllm-project/vllm-metal/${VLLM_METAL_VERSION}/install.sh" \
+        | "$backend_dir/../../../scripts/lib/extract-vllm-metal-version.sh")
     if [ -z "${VLLM_VERSION}" ]; then
         echo "ERROR: could not derive the vLLM version from vllm-metal ${VLLM_METAL_VERSION}" >&2
         exit 1
@@ -157,18 +153,10 @@ if [ "$(uname -s)" = "Darwin" ]; then
     # 2) Install the prebuilt vllm-metal wheel for the PINNED release. It pulls
     #    mlx / mlx-metal as deps and registers the `metal` platform plugin that
     #    backend.py resolves to at engine-init time. Build the release-asset URL
-    #    from the release's OWN asset listing rather than composing it from a
-    #    hardcoded platform tag: upstream raised its macOS deployment target
-    #    (macosx_11_0 -> macosx_15_0) and every composed URL started to 404.
-    #    expanded_assets is the plain release page, not api.github.com, whose
-    #    unauthenticated rate limit (60/hr per IP) 403s on shared CI runners.
-    #    The wheel version is the tag without its leading 'v'.
-    _metal_wheel=$(curl -fsSL "https://github.com/vllm-project/vllm-metal/releases/expanded_assets/${VLLM_METAL_VERSION}" \
-        | grep -oE "vllm_metal-${VLLM_METAL_VERSION#v}-cp312-cp312-[A-Za-z0-9_]+\.whl" | head -1 || true)
-    if [ -z "${_metal_wheel}" ]; then
-        echo "ERROR: no cp312 wheel asset on vllm-metal release ${VLLM_METAL_VERSION}" >&2
-        exit 1
-    fi
+    #    deterministically (tag + the cp312/arm64 wheel name) rather than querying
+    #    api.github.com, whose unauthenticated rate limit (60/hr per IP) 403s on
+    #    shared CI runners. The wheel version is the tag without its leading 'v'.
+    _metal_wheel="vllm_metal-${VLLM_METAL_VERSION#v}-cp312-cp312-macosx_11_0_arm64.whl"
     _metal_wheel_url="https://github.com/vllm-project/vllm-metal/releases/download/${VLLM_METAL_VERSION}/${_metal_wheel}"
     echo "Installing vllm-metal wheel: ${_metal_wheel_url}"
     uv pip install "${_metal_wheel_url}"

backend/python/vllm/requirements-cublas13-after.txt

@@ -3,8 +3,8 @@
 # on a cu130 host. Pull the cu130-flavoured wheel from vLLM's per-tag index
 # instead — the cublas13 case in install.sh adds --index-strategy=unsafe-best-match
 # so uv consults this index alongside PyPI.
---extra-index-url https://wheels.vllm.ai/0.28.0/cu130
+--extra-index-url https://wheels.vllm.ai/0.27.1/cu130
 # VERSION COUPLING: darwin/Apple-Silicon builds use vllm-metal (see install.sh),
 # which pins this exact vLLM version. Bumping vllm here means coordinating with a
 # vllm-metal release that supports the new version, or macOS/Metal builds break.
-vllm==0.28.0
+vllm==0.27.1

backend/python/vllm/requirements-l4t13-after.txt

@@ -9,4 +9,4 @@
 # memory architecture crash deterministically with an empty "Engine core init
 # failed" set (mudler/LocalAI#10722). Leaving this unpinned let the L4T image
 # drift onto whatever wheel was latest at build time.
-vllm==0.28.0
+vllm==0.26.0

backend/python/vllm/requirements.txt

@@ -1,4 +1,4 @@
-grpcio==1.83.1
+grpcio==1.83.0
 protobuf
 certifi
 setuptools

backend/python/vllm/test.py

@@ -121,21 +121,6 @@ class TestBackendServicer(unittest.TestCase):
         finally:
             self.tearDown()
 
-    def test_explicit_zero_temperature_and_seed_are_preserved(self):
-        """Temperature=0 is greedy decoding and 0 is a valid seed — neither is
-        an unset value. A dropped seed turns a reproducible request random."""
-        import sys, os
-        sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-        from backend import BackendServicer
-
-        servicer = BackendServicer()
-        request = backend_pb2.PredictOptions(Prompt="hello", Temperature=0, Seed=0)
-        sampling_params = servicer._build_sampling_params(request)
-        self.assertEqual(sampling_params.temperature, 0)
-        self.assertEqual(sampling_params.seed, 0)
-        # Other protobuf-default scalar fields must remain filtered.
-        self.assertEqual(sampling_params.top_p, 0.9)
-
 
     def test_messages_to_dicts(self):
         """
@@ -551,116 +536,3 @@ class TestStreamingToolParser(unittest.TestCase):
             intermediate, ["Hello ", "world", "!"],
             f"plain streaming changed; got {intermediate!r}",
         )
-
-
-class TestReasoningSplit(unittest.TestCase):
-    """Server-less tests for BackendServicer._split_reasoning.
-
-    vLLM's BaseThinkingReasoningParser returns the whole completion as
-    reasoning and None as content whenever the end token is missing. Taken
-    literally that duplicates a thinking-disabled answer into both fields.
-    """
-
-    class _Parser:
-        start_token = "<think>"
-        end_token = "</think>"
-
-    def _split(self, generated, prompt, reasoning, content):
-        import sys, os
-        sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-        from backend import BackendServicer
-        return BackendServicer._split_reasoning(
-            self._Parser(), generated, prompt, reasoning, content,
-        )
-
-    def test_thinking_off_is_not_duplicated_into_reasoning(self):
-        """No tags anywhere: the answer is content, and only content."""
-        r, c = self._split(
-            "391", "user: 17*23?\n<think>\n\n</think>\n\n",
-            reasoning="391", content=None,
-        )
-        self.assertEqual(r, "")
-        self.assertEqual(c, "391")
-
-    def test_prefilled_start_tag_keeps_truncated_reasoning(self):
-        """Prompt left the block open and the end token never arrived
-        (budget exhausted): that really is all reasoning."""
-        r, c = self._split(
-            "thinking and thinking", "user: hi\n<think>\n",
-            reasoning="thinking and thinking", content=None,
-        )
-        self.assertEqual(r, "thinking and thinking")
-        self.assertEqual(c, "")
-
-    def test_end_token_present_keeps_parser_split(self):
-        r, c = self._split(
-            "adding two and two</think>4", "user: hi\n<think>\n",
-            reasoning="adding two and two", content="4",
-        )
-        self.assertEqual(r, "adding two and two")
-        self.assertEqual(c, "4")
-
-    def test_stop_right_after_end_token_yields_empty_content(self):
-        """Content must not fall back to the raw text — that would put the
-        reasoning into the answer."""
-        r, c = self._split(
-            "reasoned</think>", "user: hi\n<think>\n",
-            reasoning="reasoned", content=None,
-        )
-        self.assertEqual(r, "reasoned")
-        self.assertEqual(c, "")
-
-    def test_unknown_token_layout_keeps_previous_behaviour(self):
-        class _Bare:
-            pass
-        import sys, os
-        sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-        from backend import BackendServicer
-        r, c = BackendServicer._split_reasoning(
-            _Bare(), "raw", "prompt", "raw", None,
-        )
-        self.assertEqual(r, "raw")
-        self.assertEqual(c, "raw")
-
-
-class TestReasoningParserConstruction(unittest.TestCase):
-    """The parser must learn whether thinking was on for this request.
-
-    vLLM's engine-based parsers (Qwen3Parser and friends) read
-    chat_template_kwargs["enable_thinking"] and default to True, so a parser
-    built without it treats a thinking-disabled completion as pure reasoning.
-    """
-
-    def _servicer(self):
-        import sys, os
-        sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-        from backend import BackendServicer
-        s = BackendServicer()
-        s.tokenizer = object()
-        return s
-
-    def test_chat_template_kwargs_are_forwarded(self):
-        seen = {}
-
-        class _Parser:
-            def __init__(self, tokenizer, **kwargs):
-                seen.update(kwargs)
-
-        s = self._servicer()
-        s.reasoning_parser_cls = _Parser
-        s._new_reasoning_parser({"enable_thinking": False})
-        self.assertEqual(
-            seen.get("chat_template_kwargs"), {"enable_thinking": False},
-        )
-
-    def test_parser_without_the_kwarg_still_builds(self):
-        """Older parsers take only the tokenizer — must not break them."""
-        class _Old:
-            def __init__(self, tokenizer):
-                self.tokenizer = tokenizer
-
-        s = self._servicer()
-        s.reasoning_parser_cls = _Old
-        self.assertIsInstance(
-            s._new_reasoning_parser({"enable_thinking": False}), _Old,
-        )

backend/python/whisperx/backend.py

@@ -16,7 +16,6 @@ import grpc
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
 from grpc_auth import get_auth_interceptors
-from transcript_utils import require_diarization_token, seconds_to_nanoseconds
 
 
 
@@ -82,11 +81,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         import whisperx
         from whisperx.diarize import DiarizationPipeline
 
-        try:
-            require_diarization_token(request.diarize, self.hf_token)
-        except ValueError as err:
-            context.abort(grpc.StatusCode.FAILED_PRECONDITION, str(err))
-
         resultSegments = []
         text = ""
         try:
@@ -123,8 +117,8 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             # Build result segments
             for idx, seg in enumerate(transcript["segments"]):
                 seg_text = seg.get("text", "")
-                start = seconds_to_nanoseconds(seg.get("start", 0))
-                end = seconds_to_nanoseconds(seg.get("end", 0))
+                start = int(seg.get("start", 0))
+                end = int(seg.get("end", 0))
                 speaker = seg.get("speaker", "")
 
                 resultSegments.append(backend_pb2.TranscriptSegment(

backend/python/whisperx/test_transcript_utils.py

@@ -1,25 +0,0 @@
-import unittest
-
-import transcript_utils
-
-
-class TestTranscriptUtils(unittest.TestCase):
-    def test_diarization_requires_hugging_face_token(self):
-        with self.assertRaisesRegex(
-            ValueError,
-            "HF_TOKEN is required for WhisperX diarization",
-        ):
-            transcript_utils.require_diarization_token(True, None)
-
-    def test_diarization_does_not_require_token_when_disabled(self):
-        transcript_utils.require_diarization_token(False, None)
-
-    def test_seconds_are_serialized_as_nanoseconds(self):
-        self.assertEqual(
-            transcript_utils.seconds_to_nanoseconds(3.25),
-            3_250_000_000,
-        )
-
-
-if __name__ == "__main__":
-    unittest.main()

backend/python/whisperx/transcript_utils.py

@@ -1,12 +0,0 @@
-"""Helpers for WhisperX transcript responses."""
-
-
-def require_diarization_token(diarize, token):
-    """Reject diarization when WhisperX cannot load its gated pipeline."""
-    if diarize and not token:
-        raise ValueError("HF_TOKEN is required for WhisperX diarization")
-
-
-def seconds_to_nanoseconds(seconds):
-    """Convert WhisperX timestamps to the duration unit used by LocalAI."""
-    return int(seconds * 1_000_000_000)

cmd/launcher/internal/launcher.go

@@ -24,17 +24,10 @@ import (
 
 // Config represents the launcher configuration
 type Config struct {
-	ModelsPath   string `json:"models_path"`
-	BackendsPath string `json:"backends_path"`
-	Address      string `json:"address"`
-	// AutoStart controls whether the launcher starts the LocalAI server as
-	// soon as the launcher itself opens (and right after a fresh install).
-	// Unset means enabled: launching the app must yield a serving endpoint,
-	// which is what the quickstart docs promise. The JSON key is deliberately
-	// not the legacy "auto_start": that field was never honored nor exposed
-	// in any UI, so every existing launcher.json carries an unintentional
-	// false that would keep auto-start permanently off (#11673).
-	AutoStart       *bool             `json:"auto_start_server"`
+	ModelsPath      string            `json:"models_path"`
+	BackendsPath    string            `json:"backends_path"`
+	Address         string            `json:"address"`
+	AutoStart       bool              `json:"auto_start"`
 	StartOnBoot     bool              `json:"start_on_boot"`
 	LogLevel        string            `json:"log_level"`
 	EnvironmentVars map[string]string `json:"environment_vars"`
@@ -129,6 +122,9 @@ func (l *Launcher) Initialize() error {
 		log.Printf("Warning: failed to cleanup partial downloads: %v", err)
 	}
 
+	if l.config.StartOnBoot {
+		l.StartLocalAI()
+	}
 	// Set default paths if not configured (only if not already loaded from config)
 	if l.config.ModelsPath == "" {
 		homeDir, _ := os.UserHomeDir()
@@ -160,12 +156,6 @@ func (l *Launcher) Initialize() error {
 		log.Printf("Setting default ShowWelcome: true")
 	}
 
-	if l.config.AutoStart == nil {
-		enabled := true
-		l.config.AutoStart = &enabled
-		log.Printf("Setting default AutoStart: true")
-	}
-
 	// Create directories
 	os.MkdirAll(l.config.ModelsPath, 0755)
 	os.MkdirAll(l.config.BackendsPath, 0755)
@@ -187,11 +177,6 @@ func (l *Launcher) Initialize() error {
 				l.showDownloadLocalAIDialog()
 			}
 		})
-	} else if l.ShouldAutoStartServer() {
-		// The launcher is a tray-only app: without this the user launches it,
-		// sees no window and no server, and concludes it does nothing (#11673).
-		log.Printf("Auto-starting LocalAI server")
-		l.autoStartServer()
 	}
 
 	// Check for updates periodically
@@ -200,35 +185,6 @@ func (l *Launcher) Initialize() error {
 	return nil
 }
 
-// ShouldAutoStartServer reports whether the launcher should start the server
-// without user interaction: at launcher startup and right after a fresh
-// install. Defaults to enabled; StartOnBoot forces a start even when
-// auto-start was explicitly disabled, preserving its historical behavior.
-func (l *Launcher) ShouldAutoStartServer() bool {
-	if l.config == nil {
-		return false
-	}
-	if l.config.StartOnBoot {
-		return true
-	}
-	return l.config.AutoStart == nil || *l.config.AutoStart
-}
-
-// autoStartServer starts LocalAI in the background and surfaces failures
-// through the systray error dialog: during an auto-start there is no visible
-// window for a regular error dialog to attach to.
-func (l *Launcher) autoStartServer() {
-	go func() {
-		if err := l.StartLocalAI(); err != nil {
-			log.Printf("Failed to auto-start LocalAI: %v", err)
-			l.updateStatus(fmt.Sprintf("Failed to start LocalAI: %v", err))
-			if l.systray != nil {
-				l.systray.showStartupErrorDialog(err)
-			}
-		}
-	}()
-}
-
 // StartLocalAI starts the LocalAI server
 func (l *Launcher) StartLocalAI() error {
 	if l.isRunning {
@@ -688,22 +644,14 @@ func (l *Launcher) showDownloadError(title, message string) {
 // after a fresh install (no LocalAI binary present yet).
 func (l *Launcher) showDownloadProgress(version, title string) {
 	l.showDownloadProgressWindow(version, title, func(win fyne.Window) {
-		message := "LocalAI has been downloaded and installed successfully. You can now start LocalAI from the launcher."
-		if l.ShouldAutoStartServer() {
-			message = "LocalAI has been downloaded and installed successfully. It will start now: manage it and open the WebUI from the system tray icon."
-		}
-		dialog.ShowConfirm("Installation Complete", message,
+		dialog.ShowConfirm("Installation Complete",
+			"LocalAI has been downloaded and installed successfully. You can now start LocalAI from the launcher.",
 			func(bool) {
 				win.Close()
 				l.updateStatus("LocalAI installed successfully")
 				if l.systray != nil {
 					l.systray.recreateMenu()
 				}
-				// A fresh install should end with a running server, not with
-				// the user hunting for a start button in the tray (#11673).
-				if l.ShouldAutoStartServer() && !l.isRunning {
-					l.autoStartServer()
-				}
 			}, win)
 	})
 }

cmd/launcher/internal/launcher_test.go

@@ -1,7 +1,6 @@
 package launcher_test
 
 import (
-	"encoding/json"
 	"os"
 	"path/filepath"
 	"strings"
@@ -56,8 +55,7 @@ var _ = Describe("Launcher", func() {
 			Expect(err).ToNot(HaveOccurred())
 
 			config := launcherInstance.GetConfig()
-			Expect(config.ShowWelcome).ToNot(BeNil())
-			Expect(*config.ShowWelcome).To(BeTrue())
+			Expect(config.ShowWelcome).To(BeTrue())
 			Expect(config.Address).To(Equal("127.0.0.1:8080"))
 			Expect(config.LogLevel).To(Equal("info"))
 		})
@@ -179,53 +177,13 @@ var _ = Describe("Launcher", func() {
 
 			assertFlagValue("--generated-content-path", filepath.Join(dataPath, "generated"))
 			assertFlagValue("--upload-path", filepath.Join(dataPath, "uploads"))
-			// The bug was the server resolving these to its shared /tmp
-			// defaults. Only reject those specific paths: on Linux the test's
-			// own temp directory legitimately lives under /tmp.
+			// The bug was the server resolving these to shared /tmp paths.
 			for _, a := range args {
-				Expect(a).ToNot(HavePrefix("/tmp/generated"), "run args must not reference the shared /tmp generated-content default, got %s", a)
-				Expect(a).ToNot(HavePrefix("/tmp/upload"), "run args must not reference the shared /tmp upload default, got %s", a)
+				Expect(a).ToNot(HavePrefix("/tmp/"), "run args must not reference shared /tmp paths, got %s", a)
 			}
 		})
 	})
 
-	// Regression for "Mac dmg launcher launches nothing" (issue #11673): the
-	// launcher created empty log files and served nothing because nothing ever
-	// started the server unless the unrelated "start on system boot" option was
-	// enabled. Launching the app must yield a serving endpoint by default.
-	Describe("ShouldAutoStartServer", func() {
-		It("should auto-start by default when nothing is configured", func() {
-			Expect(launcherInstance.ShouldAutoStartServer()).To(BeTrue())
-		})
-
-		It("should respect an explicit opt-out", func() {
-			config := launcherInstance.GetConfig()
-			err := json.Unmarshal([]byte(`{"auto_start_server": false}`), config)
-			Expect(err).ToNot(HaveOccurred())
-
-			Expect(launcherInstance.ShouldAutoStartServer()).To(BeFalse())
-		})
-
-		It("should still auto-start when StartOnBoot is set even if auto-start is off", func() {
-			config := launcherInstance.GetConfig()
-			err := json.Unmarshal([]byte(`{"auto_start_server": false, "start_on_boot": true}`), config)
-			Expect(err).ToNot(HaveOccurred())
-
-			Expect(launcherInstance.ShouldAutoStartServer()).To(BeTrue())
-		})
-
-		It("should ignore the legacy auto_start key older launchers persisted as false", func() {
-			// Old launchers marshaled the never-honored AutoStart field as
-			// "auto_start": false into every launcher.json. That stale value
-			// carries no user intent and must not disable auto-start.
-			config := launcherInstance.GetConfig()
-			err := json.Unmarshal([]byte(`{"auto_start": false}`), config)
-			Expect(err).ToNot(HaveOccurred())
-
-			Expect(launcherInstance.ShouldAutoStartServer()).To(BeTrue())
-		})
-	})
-
 	Describe("Logs", func() {
 		It("should return empty logs initially", func() {
 			logs := launcherInstance.GetLogs()
@@ -252,38 +210,13 @@ var _ = Describe("Launcher", func() {
 	})
 })
 
-// Regression for the welcome window suppressing itself (part of issue
-// #11673): the "don't show this welcome window again" checkbox was
-// initialized with the ShowWelcome value itself, so on the very first
-// showing it came up checked AND its change callback persisted
-// ShowWelcome=false, hiding the welcome window forever.
-var _ = Describe("WelcomeDontShowAgainChecked", func() {
-	It("should be unchecked when the welcome window is enabled", func() {
-		show := true
-		config := &launcher.Config{ShowWelcome: &show}
-		Expect(launcher.WelcomeDontShowAgainChecked(config)).To(BeFalse())
-	})
-
-	It("should be checked when the user opted out", func() {
-		show := false
-		config := &launcher.Config{ShowWelcome: &show}
-		Expect(launcher.WelcomeDontShowAgainChecked(config)).To(BeTrue())
-	})
-
-	It("should be unchecked when the preference is unset", func() {
-		Expect(launcher.WelcomeDontShowAgainChecked(&launcher.Config{})).To(BeFalse())
-		Expect(launcher.WelcomeDontShowAgainChecked(nil)).To(BeFalse())
-	})
-})
-
 var _ = Describe("Config", func() {
 	It("should have proper JSON tags", func() {
-		autoStart := true
 		config := &launcher.Config{
 			ModelsPath:      "/test/models",
 			BackendsPath:    "/test/backends",
 			Address:         ":8080",
-			AutoStart:       &autoStart,
+			AutoStart:       true,
 			LogLevel:        "info",
 			EnvironmentVars: map[string]string{"TEST": "value"},
 		}
@@ -291,7 +224,7 @@ var _ = Describe("Config", func() {
 		Expect(config.ModelsPath).To(Equal("/test/models"))
 		Expect(config.BackendsPath).To(Equal("/test/backends"))
 		Expect(config.Address).To(Equal(":8080"))
-		Expect(*config.AutoStart).To(BeTrue())
+		Expect(config.AutoStart).To(BeTrue())
 		Expect(config.LogLevel).To(Equal("info"))
 		Expect(config.EnvironmentVars).To(HaveKeyWithValue("TEST", "value"))
 	})

cmd/launcher/internal/ui.go

@@ -34,7 +34,6 @@ type LauncherUI struct {
 	backendsPathEntry *widget.Entry
 	addressEntry      *widget.Entry
 	logLevelSelect    *widget.Select
-	autoStartCheck    *widget.Check
 	startOnBootCheck  *widget.Check
 
 	// Environment Variables
@@ -76,7 +75,6 @@ func NewLauncherUI() *LauncherUI {
 		backendsPathEntry: widget.NewEntry(),
 		addressEntry:      widget.NewEntry(),
 		logLevelSelect:    widget.NewSelect([]string{"error", "warn", "info", "debug", "trace"}, nil),
-		autoStartCheck:    widget.NewCheck("Start LocalAI when the launcher opens", nil),
 		startOnBootCheck:  widget.NewCheck("Start LocalAI on system boot", nil),
 		logText:           widget.NewMultiLineEntry(),
 		progressBar:       widget.NewProgressBar(),
@@ -119,7 +117,6 @@ func (ui *LauncherUI) createConfigTab() *fyne.Container {
 			widget.NewLabel("Log Level:"),
 			ui.logLevelSelect,
 		),
-		ui.autoStartCheck,
 		ui.startOnBootCheck,
 	))
 
@@ -404,8 +401,6 @@ func (ui *LauncherUI) saveConfiguration() {
 	config.BackendsPath = ui.backendsPathEntry.Text
 	config.Address = ui.addressEntry.Text
 	config.LogLevel = ui.logLevelSelect.Selected
-	autoStart := ui.autoStartCheck.Checked
-	config.AutoStart = &autoStart
 	config.StartOnBoot = ui.startOnBootCheck.Checked
 
 	// Ensure environment variables are included in the configuration
@@ -588,7 +583,6 @@ func (ui *LauncherUI) LoadConfiguration() {
 	ui.backendsPathEntry.SetText(config.BackendsPath)
 	ui.addressEntry.SetText(config.Address)
 	ui.logLevelSelect.SetSelected(config.LogLevel)
-	ui.autoStartCheck.SetChecked(config.AutoStart == nil || *config.AutoStart)
 	ui.startOnBootCheck.SetChecked(config.StartOnBoot)
 
 	// Load environment variables
@@ -622,14 +616,6 @@ func (ui *LauncherUI) UpdateRunningState(isRunning bool) {
 	})
 }
 
-// WelcomeDontShowAgainChecked reports the initial state of the welcome
-// window's "don't show this welcome window again" checkbox for the given
-// config: checked only when the user has already opted out of the welcome
-// window.
-func WelcomeDontShowAgainChecked(config *Config) bool {
-	return config != nil && config.ShowWelcome != nil && !*config.ShowWelcome
-}
-
 // ShowWelcomeWindow displays the welcome window with helpful information
 func (ui *LauncherUI) ShowWelcomeWindow() {
 	if ui.launcher == nil || ui.launcher.window == nil {
@@ -691,20 +677,19 @@ Getting Started:
 			ui.openURL("https://discord.gg/XgwjKptP7Z")
 		})
 
-		// Checkbox to disable welcome window. The initial state is applied
-		// BEFORE the change callback is attached: SetChecked fires OnChanged,
-		// and letting the initialization itself persist a ShowWelcome flip is
-		// exactly the bug that suppressed this window forever after its first
-		// showing (#11673).
-		dontShowAgainCheck := widget.NewCheck("Don't show this welcome window again", nil)
-		dontShowAgainCheck.SetChecked(WelcomeDontShowAgainChecked(ui.launcher.GetConfig()))
-		dontShowAgainCheck.OnChanged = func(checked bool) {
+		// Checkbox to disable welcome window
+		dontShowAgainCheck := widget.NewCheck("Don't show this welcome window again", func(checked bool) {
 			if ui.launcher != nil {
 				config := ui.launcher.GetConfig()
 				v := !checked
 				config.ShowWelcome = &v
 				ui.launcher.SetConfig(config)
 			}
+		})
+
+		config := ui.launcher.GetConfig()
+		if config.ShowWelcome != nil {
+			dontShowAgainCheck.SetChecked(*config.ShowWelcome)
 		}
 
 		// Close button

core/application/absence_wiring.go

@@ -1,65 +0,0 @@
-// SPDX-License-Identifier: MIT
-
-package application
-
-import (
-	"fmt"
-
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/services/nodes"
-)
-
-// distributedSchedulerOptions stamps the absence wiring onto the scheduler's
-// options and returns them.
-//
-// Two assignments in a named function rather than two more fields in the
-// twenty-field literal they used to live in. The literal cannot be reached by a
-// unit spec, because the function that builds it also opens a NATS connection
-// and a database; these two lines can, and they are the two lines this whole
-// change comes down to. Losing them in the literal was silent and green.
-//
-// The grace comes from the same expression the membership loop is given
-// (Membership.SetReconnectGrace), so the window a departure is measured against
-// and the window a departure is RETAINED for cannot drift apart.
-func distributedSchedulerOptions(cfg config.DistributedConfig, presence nodes.NodePresenceReader, opts nodes.SmartRouterOptions) nodes.SmartRouterOptions {
-	opts.Presence = presence
-	opts.ReconnectGrace = cfg.ReconnectGraceOrDefault()
-	return opts
-}
-
-// requireAbsenceWiring refuses to start a distributed deployment in which
-// nothing can decide that a worker has gone away.
-//
-// Two components read absence, from one source and against one window: the
-// scheduler, which stops placing work on a departed worker, and the health
-// monitor, which stops reporting one as healthy. Each reads it through a field
-// assigned in a large construction literal in initDistributed.
-//
-// It is checked rather than assumed because losing either assignment is
-// SILENT. A scheduler with no absence source places work on workers that are
-// gone and demotes none; a health monitor with none reports a worker whose
-// tunnel died an hour ago as healthy, forever, with every request for a model
-// loaded on it failing "no route to that worker". Neither logs anything,
-// neither fails a request that would not have failed anyway, and both look
-// exactly like a fleet that is fine. Refusing to boot is the only symptom
-// either failure has, and it is the reason this is a startup error and not a
-// warning: a deployment that came up and quietly decided absence by nothing is
-// the state the tunnel work exists to remove.
-//
-// What this guard itself rests on, stated because it is a real limit: the two
-// helper functions below and above are pinned by unit specs, but the CALL to
-// this one lives in initDistributed, which opens NATS and a database and so has
-// no unit spec at all. Deleting the call, or writing a literal nil where
-// initDistributed passes the cluster registry, compiles and leaves every suite
-// in this repository green. Only tests/e2e/distributed/cluster catches it, by
-// booting the real binary: the error is returned from initDistributed and
-// aborts application startup, so a frontend so wired never comes up.
-func requireAbsenceWiring(router *nodes.SmartRouter, health *nodes.HealthMonitor) error {
-	if !router.ReadsAbsence() {
-		return fmt.Errorf("the distributed scheduler was built with no source of worker absence: it would place work on workers that have gone away and never demote one")
-	}
-	if !health.ReadsAbsence() {
-		return fmt.Errorf("the node health monitor was built with no source of worker absence: it would report a worker whose tunnel is gone as healthy indefinitely")
-	}
-	return nil
-}