mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-13 06:45:26 -04:00
8f71c08d94ddf4ce334390339b91c027ea69aec6
26
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Ettore Di Giacinto
|
2383726d6d |
Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)
Revert "chore(tests): Avoid network, sleep and more during tests (#11050)"
This reverts commit
|
||
|
Richard Palethorpeandlocalai-org-maint-bot
|
cb3bf7af3f |
chore(tests): Avoid network, sleep and more during tests (#11050)
* test: make coverage failures observable Keep per-root logs, reject concurrent coverage runs, and avoid relying on /bin/sleep in the worker timeout test. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: parallelize coverage without remote fixtures Assisted-by: Codex:gpt-5 [apply_patch] [exec_command] Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: add offline resource infrastructure Introduce versioned resource manifests, a checksum-verified CAS preparer, offline test wrappers, and a guarded network transport. Replace live Hugging Face, GitHub, and OCI cases with deterministic fixtures and inject fixture metadata into importer discovery. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: enforce offline resource replay Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: harden offline resource refresh Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: expose slow coverage waits Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: eliminate avoidable wall-clock waits Inject a clock into Hugging Face retry handling, reuse a process-scoped PostgreSQL container with per-spec schemas in the nodes suite, and poll local import jobs promptly. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: remove repeated fixture startup waits Share PostgreSQL fixtures across parallel endpoint and agent suite workers, and make the worker Free deadline injectable so the wedged-backend test does not spend five seconds on wall-clock time. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: fix offline resource CI portability Normalize Docker archive metadata before content addressing, derive archive checksums during explicit refreshes, make network lint portable to macOS, and prepare distributed images before running their offline suite. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * ci: cache Go modules before offline tests Warm the complete module graph before the Linux and macOS test jobs enter offline replay mode, so tool dependencies such as Ginkgo are not fetched through the guarded proxy. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * test: drop the static network lint in favour of real isolation The offline test suite already prevents tests from reaching the network twice over: run-test-linux-offline.sh puts the test process in a cgroup and REJECTs egress outside the private ranges, and HardenedTransport installs testnetwork.LocalGuard to refuse dials that resolve to a public address. Both fail the test with a precise error at the moment of the dial. test-network-lint.sh added neither. Its diff stage defaulted to a HEAD base, so on a clean checkout it compared the tree against itself and inspected nothing; the branch's own commits were never examined. It only produced output when an earlier job step dirtied the tree, and then it matched a bare https?:// against whatever changed. make react-ui runs npm install rather than npm ci, so CI rewrote core/http/react-ui/package-lock.json and the lint reported an npm registry URL as forbidden test network access: + "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.25.tgz", Its fingerprint stage was self-defeating in a quieter way: hashing the whole tree's network-mechanism inventory meant every rebase onto a master that touched any _test.go needed a manual baseline bump, so the check mostly caught its own staleness. Remove the script, its make target and the two prerequisite edges, along with the test-network: fixture markers that existed only to suppress it. The isolation itself is untouched. Assisted-by: Claude:claude-opus-5 [go vet] Signed-off-by: Richard Palethorpe <io@richiejp.com> * ci: keep hidden files in the offline test bundle artifact Cherry-picked from |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
8d6fdf22d3 |
fix(backends): derive the protoc generator from the protobuf runtime, regenerate stubs after late installs (#11057)
* fix(backends): choose the protoc generator from the protobuf runtime, and regenerate stubs after late installs The vLLM backends still crash on startup with VersionError: Detected incompatible Protobuf Gencode/Runtime versions when loading backend.proto: gencode 7.35.0 runtime 6.33.6 despite #10735 and #10944. Three separate defects kept it alive. 1. runProtogen picked the generator from the installed *grpcio* version. grpcio-tools' version tracks grpcio, but the gencode its bundled protoc emits tracks *protobuf*, and the two move independently: grpcio-tools 1.82.1 (the version #10735 pins to, matching grpcio 1.82.1) requires protobuf>=7.35.1 and stamps gencode 7.35.0. Pinning to grpcio could therefore never constrain the gencode. Constrain the install to the protobuf already in the venv instead and let the resolver pick the newest compatible grpcio-tools. That both selects a generator the runtime accepts and stops protogen from moving the runtime under the backend's other deps. This is self-correcting, so the hardcoded GRPCIO_TOOLS_VERSION=1.78.0 escape hatch from #10944 is no longer needed and is removed. 2. The stubs were generated too early. Most branches of vllm/install.sh (and vllm-omni) install vllm *after* installRequirements, and vllm re-resolves the protobuf runtime as it lands. Stubs generated against the pre-vllm runtime can end up newer than the runtime that finally ships, which is the ROCm failure exactly. Regenerate once the dependency set is final. 3. rm -f of the .py sources left __pycache__ behind. CPython validates a .pyc against source mtime and size, both of which can be unchanged across a regeneration (the gencode triple is the same width whether it reads 7.35.0 or 6.33.5), so a stale backend_pb2.pyc could shadow the stub just written. Also fail the build when the generated stub cannot be imported, so a gencode/runtime mismatch surfaces at image build time instead of reaching users as an opaque "grpc service not ready". Verified by driving the real runProtogen through the ROCm install sequence in a venv harness: before, gencode 7.35.0 against runtime 6.33.6 (reproducing the reported error verbatim); after, gencode 6.33.5 against runtime 6.33.6 and the stub imports cleanly. Closes #10940 Closes #10718 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-4-8[1m] [Bash] [Edit] * fix(backends): regenerate protobuf stubs in the other backends that install after installRequirements Same defect as the vllm change: installRequirements generates the stubs at the end of its own run, so any backend that installs further packages afterwards can have the protobuf runtime moved out from under stubs that were already written. The gencode stamped into backend_pb2.py then exceeds the runtime that ships and the backend dies at model load with "grpc service not ready". fish-speech already had this bug and worked around the symptom: it forces protobuf>=5.29.0 after installRequirements precisely because "transitive deps (wandb, tensorboard) may downgrade protobuf to 3.x but our generated backend_pb2.py requires protobuf 5+". Regenerating after the pin addresses the cause rather than propping up the runtime to match stale stubs. Applied to the backends whose post-installRequirements step resolves a dependency graph and can therefore move protobuf: fish-speech -e . plus an explicit protobuf install vibevoice pip install . (with deps) llama-cpp-quantization gguf / GGUF_PIP_SPEC trl gguf / GGUF_PIP_SPEC Deliberately not applied to ace-step and chatterbox (both --no-deps, so the dependency graph cannot change) or voxcpm (pins setuptools only). gguf does not depend on protobuf today, but it resolves dependencies, and "this package does not touch protobuf right now" is exactly the assumption that made the earlier fix ineffective. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-4-8[1m] [Bash] [Edit] * fix(backends): resolve the protoc generator in a throwaway env so it cannot edit the backend's pinned deps Installing grpcio-tools into the backend's own venv to generate the stubs also drags its dependencies in: grpcio-tools 1.82.1 requires grpcio>=1.82.1, so a backend that pinned grpcio==1.78.1 silently shipped 1.82.1 instead. Caught by building the llama-cpp-quantization image and reading the versions back out of the artifact: before grpcio 1.82.1 (requirements.txt pins grpcio==1.78.1) after grpcio 1.78.1 grpcio-tools absent from the venv entirely Resolve the generator in a throwaway environment instead, still constrained to the protobuf the backend ships so the gencode stays compatible. The backend's dependency set is then exactly what its requirements files declared. protoc's output is plain Python and carries no dependency on the interpreter that produced it, so generating from a different env is safe; the import check still runs under the backend's python, since that is the interpreter that has to load the stubs at model load. Verified on the rebuilt image: gencode 7.35.0, runtime protobuf 7.35.1, grpcio back at its pinned 1.78.1, and the shipped stub imports cleanly against 7.35.1. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-4-8[1m] [Bash] [Edit] * fix(backends): bound the protoc generator by BOTH the installed grpcio and protobuf The generated stubs impose two independent constraints, and every fix so far, including the previous commit on this branch, satisfied one while violating the other: backend_pb2.py needs protobuf runtime >= gencode backend_pb2_grpc.py needs installed grpcio >= grpcio-tools Resolving the generator against protobuf alone picked grpcio-tools 1.82.1 for a backend holding grpcio at 1.78.1, so the gencode was fine but the gRPC stub was not: RuntimeError: The grpc package installed is at version 1.78.1, but the generated code in backend_pb2_grpc.py depends on grpcio>=1.82.1. That is also why installing grpcio-tools into the backend venv appeared to work earlier: it dragged grpcio up to match, which was load-bearing rather than the regression it looked like. Isolating the generator removed the accidental fix and exposed the missing constraint. Bound grpcio-tools from both sides instead and let the resolver find the newest version satisfying both. The protobuf ceiling makes it back off to an older generator when the runtime trails, bounding the gencode; the grpcio ceiling keeps the _grpc stub loadable. Resolved against the four real runtime pairs observed in built images: grpcio 1.78.1 / protobuf 7.35.1 -> grpcio-tools 1.78.0, gencode 6.31.1 OK grpcio 1.78.0 / protobuf 6.33.6 -> grpcio-tools 1.78.0, gencode 6.31.1 OK grpcio 1.82.1 / protobuf 6.33.6 -> grpcio-tools 1.81.1, gencode 6.33.5 OK grpcio 1.82.1 / protobuf 7.35.1 -> grpcio-tools 1.82.1, gencode 7.35.0 OK Also restore the import check to cover backend_pb2_grpc as well as backend_pb2. Narrowing it to backend_pb2 is why the image build passed while CI failed: the guard could not see the constraint that was actually broken. Verified by running the CI sequence locally for llama-cpp-quantization, the backend whose test failed: make -C backend/python/llama-cpp-quantization -> exit 0 make -C backend/python/llama-cpp-quantization test -> exit 0, OK Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-opus-4-8[1m] [Bash] [Edit] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandlocalai-org-maint-bot
|
71e98c13a3 |
fix(vllm): generate protobuf 6 compatible stubs (#10944)
Pin vLLM protogen to grpcio-tools 1.78.0 so its generated code remains importable by protobuf 6.33.x, and remove stale generated artifacts before regeneration. Closes #10940 Assisted-by: Codex:gpt-5 [Codex] Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
d5d659bb65 |
fix(backends): pin grpcio-tools to installed grpcio in runProtogen (protobuf gencode mismatch) (#10735)
fix(backends): pin grpcio-tools to the installed grpcio in runProtogen runProtogen installed grpcio-tools unpinned, so the protoc it bundles stamped backend_pb2.py with the newest Protobuf gencode (7.35.0). When a backend caps the protobuf runtime lower -- vLLM pins protobuf to 6.33.6 -- the import-time guarantee runtime >= gencode fails: google.protobuf.runtime_version.VersionError: Detected incompatible Protobuf Gencode/Runtime versions ... gencode 7.35.0 runtime 6.33.6 The backend crashes on `import backend_pb2` before it can serve, which surfaces to the user as "grpc service not ready". It was mis-reported as a ROCm/gfx1201 failure in #10718 but is not GPU-specific and affects every vLLM variant (and any backend that caps protobuf below the latest gencode). Pin grpcio-tools to the grpcio version the backend already installed -- they release in lockstep -- so the generated gencode stays in step with the protobuf runtime. Falls back to unpinned when grpcio isn't present. Closes #10718 Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Richard Palethorpe
|
16b2d4c807 |
fix(python-backend): make JIT subprocesses work on hosts of any size (#9679)
Two related runtime fixes for Python backends that JIT-compile CUDA
kernels at first model load (FlashInfer, PyTorch inductor, triton):
1. libbackend.sh: replace `source ${EDIR}/venv/bin/activate` with a
minimal manual setup (_activateVenv: export VIRTUAL_ENV, prepend
PATH, unset PYTHONHOME) computed from $EDIR at runtime. `uv venv`
and `python -m venv` both bake the create-time absolute path into
bin/activate (e.g. VIRTUAL_ENV='/vllm/venv' from the Docker build
stage), so sourcing activate on a relocated venv — copied out of
the build container and unpacked at an arbitrary backend dir —
prepends a stale, non-existent path to $PATH. Pip-installed CLI
tools (e.g. ninja, used by FlashInfer's NVFP4 GEMM JIT) are then
never found and the load aborts with FileNotFoundError. Doing the
env setup ourselves matches what `uv run` does internally and
sidesteps the relocation problem entirely. Generic — every Python
backend benefits.
2. vllm/run.sh: replace ninja's default -j$(nproc)+2 with an adaptive
MAX_JOBS = min(nproc, (MemAvailable-4)/4). Each concurrent
nvcc/cudafe++ peaks at multiple GiB; the default OOM-kills on
memory-tight hosts (e.g. a 16 GiB desktop loading a 27B NVFP4
model) but underutilises 100-core / 1 TB boxes. User-set MAX_JOBS
still wins. Also pin NVCC_THREADS=2 unless overridden.
Refs: https://github.com/vllm-project/vllm/issues/20079
Assisted-by: Claude:claude-opus-4-7 [Edit] [Bash]
|
||
|
Ettore Di Giacinto
|
016da02845 |
feat: refactor shared helpers and enhance MLX backend functionality (#9335)
* refactor(backends): extract python_utils + add mlx_utils shared helpers
Move parse_options() and messages_to_dicts() out of vllm_utils.py into a
new framework-agnostic python_utils.py, and re-export them from vllm_utils
so existing vllm / vllm-omni imports keep working.
Add mlx_utils.py with split_reasoning() and parse_tool_calls() — ported
from mlx_vlm/server.py's process_tool_calls. These work with any
mlx-lm / mlx-vlm tool module (anything exposing tool_call_start,
tool_call_end, parse_tool_call). Used by the mlx and mlx-vlm backends in
later commits to emit structured ChatDelta.tool_calls without
reimplementing per-model parsing.
Shared smoke tests confirm:
- parse_options round-trips bool/int/float/string
- vllm_utils re-exports are identity-equal to python_utils originals
- mlx_utils parse_tool_calls handles <tool_call>...</tool_call> with a
shim module and produces a correctly-indexed list with JSON arguments
- mlx_utils split_reasoning extracts <think> blocks and leaves clean
content
* feat(mlx): wire native tool parsers + ChatDelta + token usage + logprobs
Bring the MLX backend up to the same structured-output contract as vLLM
and llama.cpp: emit Reply.chat_deltas so the OpenAI HTTP layer sees
tool_calls and reasoning_content, not just raw text.
Key insight: mlx_lm.load() returns a TokenizerWrapper that already auto-
detects the right tool parser from the model's chat template
(_infer_tool_parser in mlx_lm/tokenizer_utils.py). The wrapper exposes
has_tool_calling, has_thinking, tool_parser, tool_call_start,
tool_call_end, think_start, think_end — no user configuration needed,
unlike vLLM.
Changes in backend/python/mlx/backend.py:
- Imports: replace inline parse_options / messages_to_dicts with the
shared helpers from python_utils. Pull split_reasoning / parse_tool_calls
from the new mlx_utils shared module.
- LoadModel: log the auto-detected has_tool_calling / has_thinking /
tool_parser_type for observability. Drop the local is_float / is_int
duplicates.
- _prepare_prompt: run request.Messages through messages_to_dicts so
tool_call_id / tool_calls / reasoning_content survive the conversion,
and pass tools=json.loads(request.Tools) + enable_thinking=True (when
request.Metadata says so) to apply_chat_template. Falls back on
TypeError for tokenizers whose template doesn't accept those kwargs.
- _build_generation_params: return an additional (logits_params,
stop_words) pair. Maps RepetitionPenalty / PresencePenalty /
FrequencyPenalty to mlx_lm.sample_utils.make_logits_processors and
threads StopPrompts through to post-decode truncation.
- New _tool_module_from_tokenizer / _finalize_output / _truncate_at_stop
helpers. _finalize_output runs split_reasoning when has_thinking is
true and parse_tool_calls (using a SimpleNamespace shim around the
wrapper's tool_parser callable) when has_tool_calling is true, then
extracts prompt_tokens, generation_tokens and (best-effort) logprobs
from the last GenerationResponse chunk.
- Predict: use make_logits_processors, accumulate text + last_response,
finalize into a structured Reply carrying chat_deltas,
prompt_tokens, tokens, logprobs. Early-stops on user stop sequences.
- PredictStream: per-chunk Reply still carries raw message bytes for
back-compat but now also emits chat_deltas=[ChatDelta(content=delta)].
On loop exit, emit a terminal Reply with structured
reasoning_content / tool_calls / token counts / logprobs — so the Go
side sees tool calls without needing the regex fallback.
- TokenizeString RPC: uses the TokenizerWrapper's encode(); returns
length + tokens or FAILED_PRECONDITION if the model isn't loaded.
- Free RPC: drops model / tokenizer / lru_cache, runs gc.collect(),
calls mx.metal.clear_cache() when available, and best-effort clears
torch.cuda as a belt-and-suspenders.
* feat(mlx-vlm): mirror MLX parity (tool parsers + ChatDelta + samplers)
Same treatment as the MLX backend: emit structured Reply.chat_deltas,
tool_calls, reasoning_content, token counts and logprobs, and extend
sampling parameter coverage beyond the temp/top_p pair the backend
used to handle.
- Imports: drop the inline is_float/is_int helpers, pull parse_options /
messages_to_dicts from python_utils and split_reasoning /
parse_tool_calls from mlx_utils. Also import make_sampler and
make_logits_processors from mlx_lm.sample_utils — mlx-vlm re-uses them.
- LoadModel: use parse_options; call mlx_vlm.tool_parsers._infer_tool_parser
/ load_tool_module to auto-detect a tool module from the processor's
chat_template. Stash think_start / think_end / has_thinking so later
finalisation can split reasoning blocks without duck-typing on each
call. Logs the detected parser type.
- _prepare_prompt: convert proto Messages via messages_to_dicts (so
tool_call_id / tool_calls survive), pass tools=json.loads(request.Tools)
and enable_thinking=True to apply_chat_template when present, fall
back on TypeError for older mlx-vlm versions. Also handle the
prompt-only + media and empty-prompt + media paths consistently.
- _build_generation_params: return (max_tokens, sampler_params,
logits_params, stop_words). Maps repetition_penalty / presence_penalty /
frequency_penalty and passes them through make_logits_processors.
- _finalize_output / _truncate_at_stop: common helper used by Predict
and PredictStream to split reasoning, run parse_tool_calls against the
auto-detected tool module, build ToolCallDelta list, and extract token
counts + logprobs from the last GenerationResult.
- Predict / PredictStream: switch from mlx_vlm.generate to mlx_vlm.stream_generate
in both paths, accumulate text + last_response, pass sampler and
logits_processors through, emit content-only ChatDelta per streaming
chunk followed by a terminal Reply carrying reasoning_content,
tool_calls, prompt_tokens, tokens and logprobs. Non-streaming Predict
returns the same structured Reply shape.
- New helper _collect_media extracted from the duplicated base64 image /
audio decode loop.
- New TokenizeString RPC using the processor's tokenizer.encode and
Free RPC that drops model/processor/config, runs gc + Metal cache
clear + best-effort torch.cuda cache clear.
* feat(importer/mlx): auto-set tool_parser/reasoning_parser on import
Mirror what core/gallery/importers/vllm.go does: after applying the
shared inference defaults, look up the model URI in parser_defaults.json
and append matching tool_parser:/reasoning_parser: entries to Options.
The MLX backends auto-detect tool parsers from the chat template at
runtime so they don't actually consume these options — but surfacing
them in the generated YAML:
- keeps the import experience consistent with vllm
- gives users a single visible place to override
- documents the intended parser for a given model family
* test(mlx): add helper unit tests + TokenizeString/Free + e2e make targets
- backend/python/mlx/test.py: add TestSharedHelpers with server-less
unit tests for parse_options, messages_to_dicts, split_reasoning and
parse_tool_calls (using a SimpleNamespace shim to fake a tool module
without requiring a model). Plus test_tokenize_string and test_free
RPC tests that load a tiny MLX-quantized Llama and exercise the new
RPCs end-to-end.
- backend/python/mlx-vlm/test.py: same helper unit tests + cleanup of
the duplicated import block at the top of the file.
- Makefile: register BACKEND_MLX and BACKEND_MLX_VLM (they were missing
from the docker-build-target eval list — only mlx-distributed had a
generated target before). Add test-extra-backend-mlx and
test-extra-backend-mlx-vlm convenience targets that build the
respective image and run tests/e2e-backends with the tools capability
against mlx-community/Qwen2.5-0.5B-Instruct-4bit. The MLX backend
auto-detects the tool parser from the chat template so no
BACKEND_TEST_OPTIONS is needed (unlike vllm).
* fix(libbackend): don't pass --copies to venv unless PORTABLE_PYTHON=true
backend/python/common/libbackend.sh:ensureVenv() always invoked
'python -m venv --copies', but macOS system python (and some other
builds) refuses with:
Error: This build of python cannot create venvs without using symlinks
--copies only matters when _makeVenvPortable later relocates the venv,
which only happens when PORTABLE_PYTHON=true. Make --copies conditional
on that flag and fall back to default (symlinked) venv otherwise.
Caught while bringing up the mlx backend on Apple Silicon — the same
build path is used by every Python backend with USE_PIP=true.
* fix(mlx): support mlx-lm 0.29.x tool calling + drop deprecated clear_cache
The released mlx-lm 0.29.x ships a much simpler tool-calling API than
HEAD: TokenizerWrapper detects the <tool_call>...</tool_call> markers
from the tokenizer vocab and exposes has_tool_calling /
tool_call_start / tool_call_end, but does NOT expose a tool_parser
callable on the wrapper and does NOT ship a mlx_lm.tool_parsers
subpackage at all (those only exist on main).
Caught while running the smoke test on Apple Silicon with the
released mlx-lm 0.29.1: tokenizer.tool_parser raised AttributeError
(falling through to the underlying HF tokenizer), so
_tool_module_from_tokenizer always returned None and tool calls slipped
through as raw <tool_call>...</tool_call> text in Reply.message instead
of being parsed into ChatDelta.tool_calls.
Fix: when has_tool_calling is True but tokenizer.tool_parser is missing,
default the parse_tool_call callable to json.loads(body.strip()) — that's
exactly what mlx_lm.tool_parsers.json_tools.parse_tool_call does on HEAD
and covers the only format 0.29 detects (<tool_call>JSON</tool_call>).
Future mlx-lm releases that ship more parsers will be picked up
automatically via the tokenizer.tool_parser attribute when present.
Also tighten the LoadModel logging — the old log line read
init_kwargs.get('tool_parser_type') which doesn't exist on 0.29 and
showed None even when has_tool_calling was True. Log the actual
tool_call_start / tool_call_end markers instead.
While here, switch Free()'s Metal cache clear from the deprecated
mx.metal.clear_cache to mx.clear_cache (mlx >= 0.30), with a
fallback for older releases. Mirrored to the mlx-vlm backend.
* feat(mlx-distributed): mirror MLX parity (tool calls + ChatDelta + sampler)
Same treatment as the mlx and mlx-vlm backends: emit Reply.chat_deltas
with structured tool_calls / reasoning_content / token counts /
logprobs, expand sampling parameter coverage beyond temp+top_p, and
add the missing TokenizeString and Free RPCs.
Notes specific to mlx-distributed:
- Rank 0 is the only rank that owns a sampler — workers participate in
the pipeline-parallel forward pass via mx.distributed and don't
re-implement sampling. So the new logits_params (repetition_penalty,
presence_penalty, frequency_penalty) and stop_words apply on rank 0
only; we don't need to extend coordinator.broadcast_generation_params,
which still ships only max_tokens / temperature / top_p to workers
(everything else is a rank-0 concern).
- Free() now broadcasts CMD_SHUTDOWN to workers when a coordinator is
active, so they release the model on their end too. The constant is
already defined and handled by the existing worker loop in
backend.py:633 (CMD_SHUTDOWN = -1).
- Drop the locally-defined is_float / is_int / parse_options trio in
favor of python_utils.parse_options, re-exported under the module
name for back-compat with anything that imported it directly.
- _prepare_prompt: route through messages_to_dicts so tool_call_id /
tool_calls / reasoning_content survive, pass tools=json.loads(
request.Tools) and enable_thinking=True to apply_chat_template, fall
back on TypeError for templates that don't accept those kwargs.
- New _tool_module_from_tokenizer (with the json.loads fallback for
mlx-lm 0.29.x), _finalize_output, _truncate_at_stop helpers — same
contract as the mlx backend.
- LoadModel logs the auto-detected has_tool_calling / has_thinking /
tool_call_start / tool_call_end so users can see what the wrapper
picked up for the loaded model.
- backend/python/mlx-distributed/test.py: add the same TestSharedHelpers
unit tests (parse_options, messages_to_dicts, split_reasoning,
parse_tool_calls) that exist for mlx and mlx-vlm.
|
||
|
Ettore Di Giacinto
|
08b2b8d755 |
fix(libbackend): do not inject --index-strategy unsafe-best-match to all
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
DreamandClaude Opus 4.5
|
10a1e6c74d |
feat(whisperx): add whisperx backend for transcription with speaker diarization (#8299)
* feat(proto): add speaker field to TranscriptSegment for diarization
Add speaker field to the gRPC TranscriptSegment message and map it
through the Go schema, enabling backends to return speaker labels.
Signed-off-by: eureka928 <meobius123@gmail.com>
* feat(whisperx): add whisperx backend for transcription with diarization
Add Python gRPC backend using WhisperX for speech-to-text with
word-level timestamps, forced alignment, and speaker diarization
via pyannote-audio when HF_TOKEN is provided.
Signed-off-by: eureka928 <meobius123@gmail.com>
* feat(whisperx): register whisperx backend in Makefile
Signed-off-by: eureka928 <meobius123@gmail.com>
* feat(whisperx): add whisperx meta and image entries to index.yaml
Signed-off-by: eureka928 <meobius123@gmail.com>
* ci(whisperx): add build matrix entries for CPU, CUDA 12/13, and ROCm
Signed-off-by: eureka928 <meobius123@gmail.com>
* fix(whisperx): unpin torch versions and use CPU index for cpu requirements
Address review feedback:
- Use --extra-index-url for CPU torch wheels to reduce size
- Remove torch version pins, let uv resolve compatible versions
Signed-off-by: eureka928 <meobius123@gmail.com>
* fix(whisperx): pin torch ROCm variant to fix CI build failure
Signed-off-by: eureka928 <meobius123@gmail.com>
* fix(whisperx): pin torch CPU variant to fix uv resolution failure
Pin torch==2.8.0+cpu so uv resolves the CPU wheel from the extra
index instead of picking torch==2.8.0+cu128 from PyPI, which pulls
unresolvable CUDA dependencies.
Signed-off-by: eureka928 <meobius123@gmail.com>
* fix(whisperx): use unsafe-best-match index strategy to fix uv resolution failure
uv's default first-match strategy finds torch on PyPI before checking
the extra index, causing it to pick torch==2.8.0+cu128 instead of the
CPU variant. This makes whisperx's transitive torch dependency
unresolvable. Using unsafe-best-match lets uv consider all indexes.
Signed-off-by: eureka928 <meobius123@gmail.com>
* fix(whisperx): drop +cpu local version suffix to fix uv resolution failure
PEP 440 ==2.8.0 matches 2.8.0+cpu from the extra index, avoiding the
issue where uv cannot locate an explicit +cpu local version specifier.
This aligns with the pattern used by all other CPU backends.
Signed-off-by: eureka928 <meobius123@gmail.com>
* fix(backends): drop +rocm local version suffixes from hipblas requirements to fix uv resolution
uv cannot resolve PEP 440 local version specifiers (e.g. +rocm6.4,
+rocm6.3) in pinned requirements. The --extra-index-url already points
to the correct ROCm wheel index and --index-strategy unsafe-best-match
(set in libbackend.sh) ensures the ROCm variant is preferred.
Applies the same fix as
|
||
|
Ettore Di Giacinto
|
923ebbb344 |
feat(qwen-tts): add Qwen-tts backend (#8163)
* feat(qwen-tts): add Qwen-tts backend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Update intel deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop flash-attn for cuda13 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
|
fd53978a7b |
feat: package GPU libraries inside backend containers for unified base image (#7891)
* Initial plan * Add GPU library packaging for isolated backend environments - Create scripts/build/package-gpu-libs.sh for packaging CUDA, ROCm, SYCL, and Vulkan libraries - Update llama-cpp, whisper, stablediffusion-ggml package.sh to include GPU libraries - Update Dockerfile.python to package GPU libraries into Python backends - Update libbackend.sh to set LD_LIBRARY_PATH for GPU library loading Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> * Address code review feedback: fix variable consistency and quoting Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> * Fix code review issues: improve glob handling and remove redundant variable Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> * Simplify main Dockerfile and workflow to use unified base image - Remove GPU-specific driver installation from Dockerfile (CUDA, ROCm, Vulkan, Intel) - Simplify image.yml workflow to build single unified base image for linux/amd64 and linux/arm64 - GPU libraries are now packaged in individual backend containers Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> |
||
|
Richard PalethorpeandAlessandro Sturniolo
|
e6ba26c3e7 |
chore: Update to Ubuntu24.04 (cont #7423) (#7769)
* ci(workflows): bump GitHub Actions images to Ubuntu 24.04 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): remove CUDA 11.x support from GitHub Actions (incompatible with ubuntu:24.04) Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): bump GitHub Actions CUDA support to 12.9 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(docker): bump base image to ubuntu:24.04 and adjust Vulkan SDK/packages Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * fix(backend): correct context paths for Python backends in workflows, Makefile and Dockerfile Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(make): disable parallel backend builds to avoid race conditions Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(make): export CUDA_MAJOR_VERSION and CUDA_MINOR_VERSION for override Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(backend): update backend Dockerfiles to Ubuntu 24.04 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(backend): add ROCm env vars and default AMDGPU_TARGETS for hipBLAS builds Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(chatterbox): bump ROCm PyTorch to 2.9.1+rocm6.4 and update index URL; align hipblas requirements Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore: add local-ai-launcher to .gitignore Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): fix backends GitHub Actions workflows after rebase Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(docker): use build-time UBUNTU_VERSION variable Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(docker): remove libquadmath0 from requirements-stage base image Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(make): add backends/vllm to .NOTPARALLEL to prevent parallel builds Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * fix(docker): correct CUDA installation steps in backend Dockerfiles Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * chore(backend): update ROCm to 6.4 and align Python hipblas requirements Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): switch GitHub Actions runners to Ubuntu-24.04 for CUDA on arm64 builds Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(docker): update base image and backend Dockerfiles for Ubuntu 24.04 compatibility on arm64 Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * build(backend): increase timeout for uv installs behind slow networks on backend/Dockerfile.python Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): switch GitHub Actions runners to Ubuntu-24.04 for vibevoice backend Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * ci(workflows): fix failing GitHub Actions runners Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> * fix: Allow FROM_SOURCE to be unset, use upstream Intel images etc. Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(build): rm all traces of CUDA 11 Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(build): Add Ubuntu codename as an argument Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> Signed-off-by: Richard Palethorpe <io@richiejp.com> Co-authored-by: Alessandro Sturniolo <alessandro.sturniolo@gmail.com> |
||
|
|
1abbedd732 |
feat(diffusers): implement dynamic pipeline loader to remove per-pipeline conditionals (#7365)
* Initial plan Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add dynamic loader for diffusers pipelines and refactor backend.py Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix pipeline discovery error handling and test mock issue Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Address code review feedback: direct imports, better error handling, improved tests Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Address remaining code review feedback: specific exceptions, registry access, test imports Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add defensive fallback for DiffusionPipeline registry access Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Actually use dynamic pipeline loading for all pipelines in backend Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use dynamic loader consistently for all pipelines including AutoPipelineForText2Image Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move dynamic loader tests into test.py for CI compatibility Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Extend dynamic loader to discover any diffusers class type, not just DiffusionPipeline Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add AutoPipeline classes to pipeline registry for default model loading Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(python): set pyvenv python home Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * do pyenv update during start Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Minor changes Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> |
||
|
Ettore Di Giacinto
|
cfd95745ed |
feat: add cuda13 images (#7404)
* chore(ci): add cuda13 jobs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add to pipelines and to capabilities. Start to work on the gallery Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * gallery Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * capabilities: try to detect by looking at /usr/local Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * neutts Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backends.yaml Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add cuda13 l4t requirements.txt Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add cuda13 requirements.txt Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Pin vllm Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Not all backends are compatible Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add vllm to requirements Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * vllm is not pre-compiled for cuda 13 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
7ce92f0646 |
fix: select portable environment if detected (#6158)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
3c3f477854 |
feat(mlx-audio): Add mlx-audio backend (#6138)
* feat(mlx-audio): Add mlx-audio backend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * improve loading Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: set C_INCLUDE_PATH to point to python install Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
1ba66d00f5 |
feat: bundle python inside backends (#6123)
* feat(backends): bundle python Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test ci Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * vllm on self-hosted Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add clang Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix it for Mac * Relocate links only when is portable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Make sure to call macosPortableEnv Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use self-hosted for vllm Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
1d830ce7dd |
feat(mlx): add mlx backend (#6049)
* chore: allow to install with pip Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Make the backend to build and actually work Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * List models from system only Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add script to build darwin python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Run protogen in libbackend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Detect if mps is available across python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI: try to build backend Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Debug CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Index mlx-vlm Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Remove mlx-vlm Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop CI test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
b8eca530b6 |
feat(diffusers): add builds for nvidia-l4t (#6004)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
a8057b952c |
fix(cuda): be consistent with image tag naming (#5916)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
89040ff6f7 |
fix: add python symlink, use absolute python env path when running backends (#5664)
* fix: add python symlink, use absolute python env path when running backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(ci): do not push images when building PRs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
7ca0e2d925 |
fix(python): remove pin to setuptools, pin python version (#4395)
fix(setuptools): remove pin Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
66cf38b0b3 |
feat(venv): shared env (#3195)
* feat(venv): allow to share veenvs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(vllm): add back flash-attn Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
|
ed322bf59f |
fix: ensure correct version of torch is always installed based on BUILD_TYPE(#2890)
* fix: ensure correct version of torch is always installed based on BUILD_TYPE Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * Move causal-conv1d installation to build_types Signed-off-by: mudler <mudler@localai.io> * Move mamba-ssd install to build-type requirements.txt Signed-off-by: mudler <mudler@localai.io> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> Signed-off-by: mudler <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: mudler <mudler@localai.io> |
||
|
Simon SiebertandSimon Siebert
|
17608ea6aa |
Using exec when starting a backend instead of spawning a new process (#2720)
Co-authored-by: Simon Siebert <ansiebert@deloitte.de> |
||
|
cryptk
|
e2de8a88f7 |
feat: create bash library to handle install/run/test of python backends (#2286)
* feat: create bash library to handle install/run/test of python backends Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * chore: minor cleanup Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: remove incorrect LIMIT_TARGETS from parler-tts Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * fix: update runUnitests to handle running tests from a custom test file Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> * chore: document runUnittests Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> --------- Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com> |