* feat(llama-cpp): bump to MTP-merge SHA and document draft-mtp spec type
Update LLAMA_VERSION to 0253fb21 (post ggml-org/llama.cpp#22673 merge,
2026-05-16) to pick up Multi-Token Prediction support.
No grpc-server.cpp changes are required: the existing `spec_type` option
delegates to upstream's `common_speculative_types_from_names()`, which
already accepts the new `draft-mtp` name. The `n_rs_seq` cparam needed
by MTP is auto-derived inside `common_context_params_to_llama` from
`params.speculative.need_n_rs_seq()`, and when no `draft_model` is set
the upstream server builds the MTP context off the target model itself.
Docs: extend the speculative-decoding section of the model-configuration
guide with the new type, both load paths (MTP head embedded in the main
GGUF vs. separate `mtp-*.gguf` sibling), the PR's recommended
`spec_n_max:2-3`, and the chained `draft-mtp,ngram-mod` recipe. Also
notes that the upstream `-hf` auto-discovery of `mtp-*.gguf` siblings is
not wired through LocalAI's gRPC layer.
Agent guide: short note explaining that new upstream spec types are
picked up automatically and that MTP needs no gRPC plumbing.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama-cpp): auto-detect MTP heads and enable draft-mtp on import + load
Detect upstream's `<arch>.nextn_predict_layers` GGUF metadata key (set by
`convert_hf_to_gguf.py` for Qwen3.5/3.6 family models and similar) and,
when present and the user has not configured a `spec_type` explicitly,
auto-append the upstream-recommended speculative-decoding tuple:
- spec_type:draft-mtp
- spec_n_max:6
- spec_p_min:0.75
The 0.75 p_min is pinned defensively because upstream marks the current
default with a "change to 0.0f" TODO; locking it here keeps acceptance
thresholds stable across future llama.cpp bumps.
Detection runs in two places:
- The model importer (`POST /models/import-uri`, the `/import-model`
UI) range-fetches the GGUF header for HuggingFace / direct-URL
imports via `gguf.ParseGGUFFileRemote`, with a 30s timeout and
non-fatal error handling. OCI/Ollama URIs are skipped because the
artifact is not directly streamable; the load-time hook covers them
once the file is on disk.
- The llama-cpp load-time hook (`guessGGUFFromFile`) reads the local
header on every model start and appends the same options if
`spec_type` is not already set.
Both paths share `ApplyMTPDefaults` and respect an explicit user-set
`spec_type:` / `speculative_type:` so YAML overrides win. Ginkgo
specs cover the append, preserve-user-choice, legacy alias, and nil
safety paths.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(importer): resolve huggingface:// URIs before MTP header probe
`gguf.ParseGGUFFileRemote` only speaks HTTP(S), but the importer was
handing it the raw `huggingface://...` URI directly (and similarly for
any other custom downloader scheme). Live-test against
`huggingface://ggml-org/Qwen3.6-27B-MTP-GGUF/Qwen3.6-27B-MTP-Q8_0.gguf`
exposed this: the probe failed with `unsupported protocol scheme
"huggingface"`, was caught by the non-fatal error path, and the MTP
options were silently never applied to the generated YAML.
Route every candidate URI through `downloader.URI.ResolveURL()` and
require the resolved form to be HTTP(S). After the fix the probe
successfully reads `<arch>.nextn_predict_layers=1` from the real HF
GGUF and the emitted ConfigFile carries spec_type:draft-mtp,
spec_n_max:6, spec_p_min:0.75 as intended.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
The llama.cpp backend already accepts a free-form options: array in the
model config that maps to common_params fields, but a coverage audit
against upstream pin 7f3f843c flagged 12 user-visible knobs that were
neither set via the typed proto fields nor reachable via options:.
Wire them up under the existing if/else chain in params_parse, before
the speculative section. Each new option follows the file's prevailing
patterns (try/catch around numeric parses, the same true/1/yes/on bool
form used elsewhere, hardware_concurrency() fallback for thread counts,
mirror of draft_override_tensor for override_tensor).
Top-level / batching / IO:
- n_ubatch (alias ubatch) -- physical batch size; was previously
force-aliased to n_batch at line 482, blocking embedding/rerank
workloads that need independent control
- threads_batch (alias n_threads_batch) -- main-model batch threads;
mirrors the existing draft_threads_batch
- direct_io (alias use_direct_io) -- O_DIRECT model loads
- verbosity -- llama.cpp log threshold (line 479 had this commented
out)
- override_tensor (alias tensor_buft_overrides) -- per-tensor buffer
overrides for the main model; mirrors draft_override_tensor
Embedding / multimodal:
- pooling_type (alias pooling) -- mean/cls/last/rank/none; previously
only auto-flipped to RANK for rerankers
- embd_normalize (alias embedding_normalize) -- and the embedding
handler now reads params_base.embd_normalize instead of a hardcoded
2 at the previous embd_normalize literal in Embedding()
- mmproj_use_gpu (alias mmproj_offload) -- mmproj on CPU vs GPU
- image_min_tokens / image_max_tokens -- per-image vision token budget
Reasoning surface (the audit-focus three; LocalAI's existing
ReasoningConfig.DisableReasoning only feeds the per-request
chat_template_kwargs.enable_thinking and does not touch any of these):
- reasoning_format -- none/auto/deepseek/deepseek-legacy parser
- enable_reasoning (alias reasoning_budget) -- -1/0/>0 thinking budget
- prefill_assistant -- trailing-assistant-message prefill toggle
All 14 referenced fields exist on both the upstream pin and the
turboquant fork's common.h, so no LOCALAI_LEGACY_LLAMA_CPP_SPEC guard
is needed.
Docs: extend model-configuration.md with new "Reasoning Models",
"Multimodal Backend Options", "Embedding & Reranking Backend Options",
and "Other Backend Tuning Options" subsections; also refresh the
Speculative Type Values table to show the new dash-separated canonical
names alongside the underscore aliases LocalAI still accepts.
Assisted-by: claude-code:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ⬆️ Update ggml-org/llama.cpp
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* fix(llama-cpp): adapt to upstream COMMON_SPECULATIVE_TYPE_DRAFT rename
ggml-org/llama.cpp#22964 ("spec: update CLI arguments for better
consistency") renamed the speculative type enum values:
COMMON_SPECULATIVE_TYPE_DRAFT -> COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE
COMMON_SPECULATIVE_TYPE_EAGLE3 -> COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3
and the registered name strings flipped from underscore- to dash-
separated form (e.g. ngram_simple -> ngram-simple), with the bare
draft/eagle3 aliases replaced by draft-simple/draft-eagle3.
This broke the build with the new LLAMA_VERSION on every variant
(vulkan/arm64, darwin and likely all the rest) at grpc-server.cpp:461.
Update the upstream branch of the speculative-type fallback to use the
new identifier (the LOCALAI_LEGACY_LLAMA_CPP_SPEC fork branch keeps the
old name), and normalize spec_type option tokens before passing them to
common_speculative_types_from_names so existing model configs that say
spec_type:draft / spec_type:ngram_simple keep working.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude-code:claude-opus-4-7
---------
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* feat(liquid-audio): add LFM2.5-Audio any-to-any backend + realtime_audio usecase
Wires LiquidAI's LFM2.5-Audio-1.5B as a self-contained Realtime API model:
single engine handles VAD, transcription, LLM, and TTS in one bidirectional
stream — drop-in alternative to a VAD+STT+LLM+TTS pipeline.
Backend
- backend/python/liquid-audio/ — new Python gRPC backend wrapping the
`liquid-audio` package. Modes: chat / asr / tts / s2s, voice presets,
Load/Predict/PredictStream/AudioTranscription/TTS/VAD/AudioToAudioStream/
Free and StartFineTune/FineTuneProgress/StopFineTune. Runtime monkey-patch
on `liquid_audio.utils.snapshot_download` so absolute local paths from
LocalAI's gallery resolve without a HF round-trip. soundfile in place of
torchaudio.load/save (torchcodec drags NVIDIA NPP we don't bundle).
- backend/backend.proto + pkg/grpc/{backend,client,server,base,embed,
interface}.go — new AudioToAudioStream RPC mirroring AudioTransformStream
(config/frame/control oneof in; typed event+pcm+meta out).
- core/services/nodes/{health_mock,inflight}_test.go — add stubs for the
new RPC to the test fakes.
Config + capabilities
- core/config/backend_capabilities.go — UsecaseRealtimeAudio, MethodAudio
ToAudioStream, UsecaseInfoMap entry, liquid-audio BackendCapability row.
- core/config/model_config.go — FLAG_REALTIME_AUDIO bitmask, ModalityGroups
membership in both speech-input and audio-output groups so a lone flag
still reads as multimodal, GetAllModelConfigUsecases entry, GuessUsecases
branch.
Realtime endpoint
- core/http/endpoints/openai/realtime.go — extract prepareRealtimeConfig()
so the gate is unit-testable; accept realtime_audio models and self-fill
empty pipeline slots with the model's own name (user-pinned slots win).
- core/http/endpoints/openai/realtime_gate_test.go — six specs covering nil
cfg, empty pipeline, legacy pipeline, self-contained realtime_audio,
user-pinned VAD slot, and partial legacy pipeline.
UI + endpoints
- core/http/routes/ui.go — /api/pipeline-models accepts either a legacy
VAD+STT+LLM+TTS pipeline or a realtime_audio model; surfaces a
self_contained flag so the Talk page can collapse the four cards.
- core/http/routes/ui_api.go — realtime_audio in usecaseFilters.
- core/http/routes/ui_pipeline_models_test.go — covers both code paths.
- core/http/react-ui/src/pages/Talk.jsx — self-contained badge instead of
the four-slot grid; rename Edit Pipeline → Edit Model Config; less
pipeline-specific wording.
- core/http/react-ui/src/pages/Models.jsx + locales/en/models.json — new
realtime_audio filter button + i18n.
- core/http/react-ui/src/utils/capabilities.js — CAP_REALTIME_AUDIO.
- core/http/react-ui/src/pages/FineTune.jsx — voice + validation-dataset
fields, surfaced when backend === liquid-audio, plumbed via
extra_options on submit/export/import.
Gallery + importer
- gallery/liquid-audio.yaml — config template with known_usecases:
[realtime_audio, chat, tts, transcript, vad].
- gallery/index.yaml — four model entries (realtime/chat/asr/tts) keyed by
mode option. Fixed pre-existing `transcribe` typo on the asr entry
(loader silently dropped the unknown string → entry never surfaced as a
transcript model).
- gallery/lfm.yaml — function block for the LFM2 Pythonic tool-call format
`<|tool_call_start|>[name(k="v")]<|tool_call_end|>` matching
common_chat_params_init_lfm2 in vendored llama.cpp.
- core/gallery/importers/{liquid-audio,liquid-audio_test}.go — detector
matches LFM2-Audio HF repos (excludes -gguf mirrors); mode/voice
preferences plumbed through to options.
- core/gallery/importers/importers.go — register LiquidAudioImporter
before LlamaCPPImporter.
- pkg/functions/parse_lfm2_test.go — seven specs for the response/argument
regex pair on the LFM2 pythonic format.
Build matrix
- .github/backend-matrix.yml — seven liquid-audio targets (cuda12, cuda13,
l4t-cuda-13, hipblas, intel, cpu amd64, cpu arm64). Jetpack r36 cuda-12
is skipped (Ubuntu 22.04 / Python 3.10 incompatible with liquid-audio's
3.12 floor).
- backend/index.yaml — anchor + 13 image entries.
- Makefile — .NOTPARALLEL, prepare-test-extra, test-extra,
docker-build-liquid-audio.
Docs
- .agents/plans/liquid-audio-integration.md — phased plan; PR-D (real
any-to-any wiring via AudioToAudioStream), PR-E (mid-audio tool-call
detector), PR-G (GGUF entries once upstream llama.cpp PR #18641 lands)
remain.
- .agents/api-endpoints-and-auth.md — expand the capability-surface
checklist with every place a new FLAG_* needs to be registered.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): function calling + history cap for any-to-any models
Three pieces, all on the realtime_audio path that just landed:
1. liquid-audio backend (backend/python/liquid-audio/backend.py):
- _build_chat_state grows a `tools_prelude` arg.
- new _render_tools_prelude parses request.Tools (the OpenAI Chat
Completions function array realtime.go already serialises) and
emits an LFM2 `<|tool_list_start|>…<|tool_list_end|>` system turn
ahead of the user history. Mirrors gallery/lfm.yaml's `function:`
template so the model sees the same prompt shape whether served
via llama-cpp or here. Without this the backend silently dropped
tools — function calling was wired end-to-end on the Go side but
the model never saw a tool list.
2. Realtime history cap (core/http/endpoints/openai/realtime.go):
- Session grows MaxHistoryItems int; default picked by new
defaultMaxHistoryItems(cfg) — 6 for realtime_audio models (LFM2.5
1.5B degrades quickly past a handful of turns), 0/unlimited for
legacy pipelines composing larger LLMs.
- triggerResponse runs conv.Items through trimRealtimeItems before
building conversationHistory. Helper walks the cut left if it
would orphan a function_call_output, so tool result + call pairs
stay intact.
- realtime_gate_test.go: specs for defaultMaxHistoryItems and
trimRealtimeItems (zero cap, under cap, over cap, tool-call pair
preservation).
3. Talk page (core/http/react-ui/src/pages/Talk.jsx):
- Reuses the chat page's MCP plumbing — useMCPClient hook,
ClientMCPDropdown component, same auto-connect/disconnect effect
pattern. No bespoke tool registry, no new REST endpoints; tools
come from whichever MCP servers the user toggles on, exactly as
on the chat page.
- sendSessionUpdate now passes session.tools=getToolsForLLM(); the
update re-fires when the active server set changes mid-session.
- New response.function_call_arguments.done handler executes via
the hook's executeTool (which round-trips through the MCP client
SDK), then replies with conversation.item.create
{type:function_call_output} + response.create so the model
completes its turn with the tool output. Mirrors chat's
client-side agentic loop, translated to the realtime wire shape.
UI changes require a LocalAI image rebuild (Dockerfile:308-313 bakes
react-ui/dist into the runtime image). Backend.py changes can be
swapped live in /backends/<id>/backend.py + /backend/shutdown.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): LocalAI Assistant ("Manage Mode") for the Talk page
Mirrors the chat-page metadata.localai_assistant flow so users can ask the
realtime model what's loaded / installed / configured. Tools are run
server-side via the same in-process MCP holder that powers the chat
modality — no transport switch, no proxy, no new wire protocol.
Wire:
- core/http/endpoints/openai/realtime.go:
- RealtimeSessionOptions{LocalAIAssistant,IsAdmin}; isCurrentUserAdmin
helper mirrors chat.go's requireAssistantAccess (no-op when auth
disabled, else requires auth.RoleAdmin).
- Session grows AssistantExecutor mcpTools.ToolExecutor.
- runRealtimeSession, when opts.LocalAIAssistant is set: gate on admin,
fail closed if DisableLocalAIAssistant or the holder has no tools,
DiscoverTools and inject into session.Tools, prepend
holder.SystemPrompt() to instructions.
- Tool-call dispatch loop: when AssistantExecutor.IsTool(name), run
ExecuteTool inproc, append a FunctionCallOutput to conv.Items, skip
the function_call_arguments client emit (the client can't execute
these — it doesn't know about them). After the loop, if any
assistant tool ran, trigger another response so the model speaks the
result. Mirrors chat's agentic loop, driven server-side rather than
via client round-trip.
- core/http/endpoints/openai/realtime_webrtc.go: RealtimeCallRequest
gains `localai_assistant` (JSON omitempty). Handshake calls
isCurrentUserAdmin and builds RealtimeSessionOptions.
- core/http/react-ui/src/pages/Talk.jsx: admin-only "Manage Mode"
checkbox under the Tools dropdown; passes localai_assistant: true to
realtimeApi.call's body, captured in the connect callback's deps.
Mirroring chat's pattern means the in-process MCP tools surface "just
works" for the Talk page without exposing a Streamable-HTTP MCP endpoint
(which was the alternative). Clients with their own MCP servers can
still use the existing ClientMCPDropdown path in parallel; the realtime
handler distinguishes them by AssistantExecutor.IsTool() at dispatch
time.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): render Manage Mode tool calls in the Talk transcript
Previously the realtime endpoint only emitted response.output_item.added
for the FunctionCall item, and Talk.jsx's switch ignored the event — so
server-side tool runs were invisible in the UI. The model would speak
the result but the user had no way to see what tool was actually
called.
realtime.go: after executing an assistant tool inproc, emit a second
output_item.added/.done pair for the FunctionCallOutput item. Mirrors
the way the chat page displays tool_call + tool_result blocks.
Talk.jsx: handle both response.output_item.added and .done. Render
FunctionCall (with arguments) and FunctionCallOutput (pretty-printed
JSON when possible) as two transcript entries — `tool_call` with the
wrench icon, `tool_result` with the clipboard icon, both in mono-space
secondary-colour. Resets streamingRef after the result so the next
assistant text delta starts a fresh transcript entry instead of
appending to the previous turn.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* refactor(realtime): bound the Manage Mode tool-loop + preserve assistant tools
Fallout from a review pass on the Manage Mode patches:
- Bound the server-side agentic loop. triggerResponse used to recurse on
executedAssistantTool with no cap — a model that kept calling tools
would blow the goroutine stack. New maxAssistantToolTurns = 10 (mirrors
useChat.js's maxToolTurns). Public triggerResponse is now a thin shim
over triggerResponseAtTurn(toolTurn int); recursion increments the
counter and stops at the cap with an xlog.Warn.
- Preserve Manage Mode tools across client session.update. The handler
used to blindly overwrite session.Tools, so toggling a client MCP
server mid-session silently wiped the in-process admin tools. Session
now caches the original AssistantTools slice at session creation and
the session.update handler merges them back in (client names win on
collision — the client is explicit).
- strconv.ParseBool for the localai_assistant query param instead of
hand-rolled "1" || "true". Mirrors LocalAIAssistantFromMetadata.
- Talk.jsx: render both tool_call and tool_result on
response.output_item.done instead of splitting them across .added and
.done. The server's event pairing (added → done) stays correct; the
UI just doesn't need to inspect both phases of the same item. One
switch case instead of two, no behavioural change.
Out of scope (noted for follow-ups): extract a shared assistant-tools
helper between chat.go and realtime.go (duplication is small enough
that two parallel implementations stay readable for now), and an i18n
key for the Manage Mode helper text (Talk.jsx doesn't use i18n
anywhere else yet).
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* ci(test-extra): wire liquid-audio backend smoke test
The backend ships test.py + a `make test` target and is listed in
backend-matrix.yml, so scripts/changed-backends.js already writes a
`liquid-audio=true|false` output when files under backend/python/liquid-audio/
change. The workflow just wasn't reading it.
- Expose the `liquid-audio` output on the detect-changes job
- Add a tests-liquid-audio job that runs `make` + `make test` in
backend/python/liquid-audio, gated on the per-backend detect flag
The smoke covers Health() and LoadModel(mode:finetune); fine-tune mode
short-circuits before any HuggingFace download (backend.py:192), so the
job needs neither weights nor a GPU. The full-inference path remains
gated on LIQUID_AUDIO_MODEL_ID, which CI doesn't set.
The four new Go test files (core/gallery/importers/liquid-audio_test.go,
core/http/endpoints/openai/realtime_gate_test.go,
core/http/routes/ui_pipeline_models_test.go, pkg/functions/parse_lfm2_test.go)
are already picked up by the existing test.yml workflow via `make test` →
`ginkgo -r ./pkg/... ./core/...`; their packages all carry RunSpecs entries.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(llama.cpp): bump to 1ec7ba0c14f33f17e980daeeda5f35b225d41994
Picks up the upstream `spec : parallel drafting support` change
(ggml-org/llama.cpp#22838) which reshapes the speculative-decoding API
and `server_context_impl`.
Adapt the grpc-server wrapper accordingly:
* `common_params_speculative::type` (single enum) became `types`
(`std::vector<common_speculative_type>`). Update both the
"default to draft when a draft model is set" branch and the
`spec_type`/`speculative_type` option parser. The parser now also
tolerates comma-separated lists, mirroring the upstream
`common_speculative_types_from_names` semantics.
* `common_params_speculative_draft::n_ctx` is gone (draft now shares
the target context size). Keep the `draft_ctx_size` option name for
backward compatibility and ignore the value rather than failing.
* `server_context_impl::model` was renamed to `model_tgt`; update the
two reranker / model-metadata call sites.
Replaces #9763. Builds cleanly under the linux/amd64 cpu-llama-cpp
target locally.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama-cpp): expose new speculative-decoding option keys
Upstream `spec : parallel drafting support` (ggml-org/llama.cpp#22838)
adds the `ngram_mod`, `ngram_map_k`, and `ngram_map_k4v` speculative
families and beefs up the draft-model knobs. The previous bump only
adapted the API; this exposes the new fields through the grpc-server
options dictionary so model configs can drive them.
New `options:` keys (all under `backend: llama-cpp`):
ngram_mod (`ngram_mod` type):
spec_ngram_mod_n_min / spec_ngram_mod_n_max / spec_ngram_mod_n_match
ngram_map_k (`ngram_map_k` type):
spec_ngram_map_k_size_n / spec_ngram_map_k_size_m / spec_ngram_map_k_min_hits
ngram_map_k4v (`ngram_map_k4v` type):
spec_ngram_map_k4v_size_n / spec_ngram_map_k4v_size_m /
spec_ngram_map_k4v_min_hits
ngram lookup caches (`ngram_cache` type):
spec_lookup_cache_static / lookup_cache_static
spec_lookup_cache_dynamic / lookup_cache_dynamic
Draft-model tuning (active when `spec_type` is `draft`):
draft_cache_type_k / spec_draft_cache_type_k
draft_cache_type_v / spec_draft_cache_type_v
draft_threads / spec_draft_threads
draft_threads_batch / spec_draft_threads_batch
draft_cpu_moe / spec_draft_cpu_moe (bool flag)
draft_n_cpu_moe / spec_draft_n_cpu_moe (first N MoE layers on CPU)
draft_override_tensor / spec_draft_override_tensor
(comma-separated <tensor regex>=<buffer type>; re-implements upstream's
static parse_tensor_buffer_overrides since it isn't exported)
`spec_type` already accepted comma-separated lists after the previous
commit, matching upstream's `common_speculative_types_from_names`.
Docs: refresh `docs/content/advanced/model-configuration.md` with
per-family tables and a note about multi-type chaining.
Builds locally with `make docker-build-llama-cpp` (linux/amd64
cpu-llama-cpp AVX variant).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(turboquant): bridge new llama.cpp spec API to the legacy fork layout
The previous commits in this series adapted backend/cpp/llama-cpp/grpc-server.cpp
to the post-#22838 (parallel drafting) llama.cpp API. The turboquant build
reuses the same grpc-server.cpp through backend/cpp/turboquant/Makefile,
which copies it into turboquant-<flavor>-build/ and runs patch-grpc-server.sh
on the copy. The fork branched before the API refactor, so it errors out on:
* `ctx_server.impl->model_tgt` (fork still has `model`)
* `params.speculative.{ngram_mod,ngram_map_k,ngram_map_k4v,ngram_cache}.*`
(none of these sub-structs exist in the fork)
* `params.speculative.draft.{cache_type_k/v, cpuparams[, _batch].n_threads,
tensor_buft_overrides}` (fork uses the pre-#22397 flat layout)
* `params.speculative.types` vector / `common_speculative_types_from_names`
(fork has a scalar `type` and only the singular helper)
Approach:
1. backend/cpp/llama-cpp/grpc-server.cpp: introduce a single feature switch
`LOCALAI_LEGACY_LLAMA_CPP_SPEC`. When defined, the two `speculative.type[s]`
discriminations (the "default to draft when a draft model is set" branch
and the `spec_type` / `speculative_type` option parser) fall back to the
singular scalar form, and the entire new-option block (ngram_mod / map_k
/ map_k4v / ngram_cache / draft.{cache_type_*, cpuparams*,
tensor_buft_overrides}) is preprocessed out. The macro is *not* defined
in the source tree — stock llama-cpp builds get the full new API.
2. backend/cpp/turboquant/patch-grpc-server.sh: two new patch steps applied
to the per-flavor build copy at turboquant-<flavor>-build/grpc-server.cpp:
- substitute `ctx_server.impl->model_tgt` -> `ctx_server.impl->model`
- inject `#define LOCALAI_LEGACY_LLAMA_CPP_SPEC 1` before the first
`#include`, so the guarded blocks above drop out for the fork build.
Both patches are idempotent and follow the existing sed/awk pattern in
this script (KV cache types, `get_media_marker`, flat speculative
renames). Stock llama-cpp's `grpc-server.cpp` is never touched.
Drop both legacy patches once the turboquant fork rebases past
ggml-org/llama.cpp#22397 / #22838.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(turboquant): close draft_ctx_size brace inside legacy guard
The previous turboquant fix wrapped the new option-handler blocks in
`#ifndef LOCALAI_LEGACY_LLAMA_CPP_SPEC ... #endif` but placed the guard
in the middle of an `else if` chain — the `} else if` openings of the
new blocks were responsible for closing the previous block's brace.
With the macro defined the new blocks vanish, draft_ctx_size's `{`
loses its closer, the for-loop's `}` is consumed instead, and the
file ends with a stray opening brace — clang reports it as
`function-definition is not allowed here before '{'` on the next
top-level `int main(...)` and `expected '}' at end of input`.
Move the chain split inside the draft_ctx_size branch:
} else if (... "draft_ctx_size") {
// ...
#ifdef LOCALAI_LEGACY_LLAMA_CPP_SPEC
} // legacy: chain ends here
#else
} else if (... "spec_ngram_mod_n_min") { // modern: chain continues
...
} else if (... "draft_override_tensor") {
...
} // closes last branch
#endif
} // closes for-loop
Brace count is now balanced under both preprocessor branches (verified
with `tr -cd '{' | wc -c` against the patched and unpatched outputs).
Local `make docker-build-turboquant` builds the linux/amd64 cpu-llama-cpp
`turboquant-avx` variant cleanly.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ci): forward AMDGPU_TARGETS into Dockerfile.turboquant builder-prebuilt
Dockerfile.turboquant's `builder-prebuilt` stage was missing the
`ARG AMDGPU_TARGETS` / `ENV AMDGPU_TARGETS=${AMDGPU_TARGETS}` pair that
`builder-fromsource` already has (and that `Dockerfile.llama-cpp`
mirrors across both stages). When CI uses the prebuilt base image
(quay.io/go-skynet/ci-cache:base-grpc-*, the common path) the build-arg
passed by the workflow never reaches the env inside the compile stage.
backend/cpp/llama-cpp/Makefile:38 (introduced by #9626) errors out on
hipblas builds when AMDGPU_TARGETS is empty, and the turboquant
Makefile reuses backend/cpp/llama-cpp via a sibling build dir, so the
same check fires from turboquant-fallback under BUILD_TYPE=hipblas:
Makefile:38: *** AMDGPU_TARGETS is empty — set it to a comma-separated
list of gfx targets e.g. gfx1100,gfx1101. Stop.
make: *** [Makefile:66: turboquant-fallback] Error 2
The bug is latent on master because the docker layer cache stays warm
across builds — the compile step rarely re-runs from scratch. The
llama.cpp bump in this PR invalidates the cache, so the missing env var
becomes load-bearing and the hipblas turboquant CI job fails.
Mirror the existing pattern from Dockerfile.llama-cpp.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ci(bump-deps): register ds4 + move version pin into the Makefile
The initial ds4 PR (#9758) put the upstream commit pin in
backend/cpp/ds4/prepare.sh as a shell variable. The auto-bump bot at
.github/bump_deps.sh greps for ^$VAR?= in a Makefile, so DS4_VERSION
was invisible to it - other backends (llama-cpp, ik-llama-cpp,
turboquant, voxtral, etc.) all pin in their Makefile.
This change:
- Moves DS4_VERSION?= and DS4_REPO?= to the top of
backend/cpp/ds4/Makefile.
- Inlines the git init/fetch/checkout recipe into the 'ds4:' target
(matches llama-cpp's 'llama.cpp:' target pattern). Directory acts
as the target so make only re-clones when missing.
- Deletes the now-redundant prepare.sh.
- Adds antirez/ds4 + DS4_VERSION + main + backend/cpp/ds4/Makefile to
the .github/workflows/bump_deps.yaml matrix so the daily bot opens
PRs against this pin.
- Updates .agents/ds4-backend.md to point at the Makefile.
Verified:
$ grep -m1 '^DS4_VERSION?=' backend/cpp/ds4/Makefile
DS4_VERSION?=ae302c2fa18cc6d9aefc021d0f27ae03c9ad2fc0
$ make -C backend/cpp/ds4 ds4 # clones into ds4/ at the pin
$ make -C backend/cpp/ds4 ds4 # no-op on second invocation
make: 'ds4' is up to date.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: route backend/cpp/ds4/ changes through changed-backends.js
scripts/changed-backends.js:inferBackendPath has an explicit branch per
cpp dockerfile suffix (ik-llama-cpp, turboquant, llama-cpp). Without a
matching branch the function returns null, the backend never lands in
the path map, and PR change-detection cannot map "backend/cpp/ds4/X
changed" -> "rebuild ds4 image".
This is why PR #9761 produced zero ds4 jobs even though it directly
edits backend/cpp/ds4/Makefile.
Adds the missing branch (Dockerfile.ds4 -> backend/cpp/ds4/), placed
before the llama-cpp branch (since both share the .cpp ancestry but
ds4 is more specific - same ordering rule documented in
.agents/adding-backends.md).
Verified with a local Node simulation of the script against this PR's
diff: the path map now contains 'ds4 -> backend/cpp/ds4/' and a
'backend/cpp/ds4/Makefile' change correctly triggers the ds4 backend
in the rebuild set.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* docs(adding-backends): harden the two gotchas that bit ds4
Both omissions are silent at the time you ADD a backend - the failure
mode only appears later (the bump bot stays silent forever, or the path
filter shows up on the next PR that touches your backend with zero CI
jobs and looks broken for unrelated reasons). Expanding the
`scripts/changed-backends.js` paragraph from a one-liner to a fully
worked example, and adding a new sibling paragraph for the
`bump_deps.yaml` + Makefile-pin contract.
Both call out the specific mistakes from the ds4 timeline (#9758
→ #9761) so future contributors can pattern-match on the cause.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* test(e2e-backends): allow BACKEND_BINARY for native-built backends
Adds an escape hatch for hardware-gated backends (e.g. ds4) where the
model is too large for Docker build context. When BACKEND_BINARY points
at a run.sh produced by 'make -C backend/cpp/<name> package', the suite
skips docker image extraction and drives the binary directly.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(e2e-backends): validate BACKEND_BINARY basename + log actual source
Two follow-ups from the cbcf5148 code review:
- BACKEND_BINARY now requires a path whose basename is `run.sh`. Without
this check, `filepath.Dir(binary)` silently discarded the filename, so
pointing the env var at an arbitrary binary failed later with a
confusing assertion that named a path the user never typed.
- The "Testing image=..." debug line printed an empty string when the
binary path was used, hiding the actual source in CI logs. The line
now reports whichever of BACKEND_IMAGE / BACKEND_BINARY is in effect
as `src=...`.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): scaffold ds4 backend dir
Adds prepare.sh, run.sh, and a .gitignore. CMakeLists, Makefile, and the
implementation arrive in follow-up commits.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): add backend Makefile
Drives ds4's upstream Makefile to produce engine .o files (CUDA on Linux
when BUILD_TYPE=cublas, Metal on Darwin, otherwise CPU debug path), then
invokes CMake on our wrapper.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): add CMakeLists for grpc-server
Generates protoc stubs from backend.proto, links grpc-server.cpp +
dsml_parser.cpp + dsml_renderer.cpp + kv_cache.cpp against pre-built
ds4 engine .o files. DS4_GPU=cuda|metal|cpu selects the backend.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): grpc-server skeleton + module stubs
The minimum that links: Backend service with Health + Free; other RPCs
default to UNIMPLEMENTED. Stub headers/sources for dsml_parser,
dsml_renderer, and kv_cache are in place so CMake links cleanly even
before those modules ship.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): implement LoadModel
Opens engine + creates session sized to ContextSize (default 32768).
Backend is compile-time: CPU when DS4_NO_GPU, Metal on __APPLE__, else
CUDA. MTP/speculative options are accepted via ModelOptions.Options[]
(mtp_path, mtp_draft, mtp_margin). kv_cache_dir option is captured into
g_kv_cache_dir for the cache module (Task 19 wires it in).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): implement TokenizeString
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): implement Predict (plain text)
Tool calls + thinking-mode split arrive in Task 13 once dsml_parser is in.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): implement PredictStream (plain text)
ChatDelta + reasoning/tool_calls split arrives in Task 14.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): implement Status RPC
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): add DSML streaming parser
Classifies raw model-emitted token text into CONTENT / REASONING /
TOOL_START / TOOL_ARGS / TOOL_END events. Markers it watches for are the
literal DSML strings rendered by ds4_server.c's prompt template
(<｜DSML｜tool_calls>, <｜DSML｜invoke name=...>, <think>, etc.) - these are
plain text the model emits, not special tokens.
Partial markers split across token chunks are buffered until a full marker
or a definitively-not-a-marker '<' is observed. RandomToolId() generates
the API-side tool call id (call_xxx) that exact-replay would key on.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(backend/cpp/ds4): split hex escapes in DSML markers + add cstring/cstdio includes
C++ \x hex escapes have no length cap. '\x9cD' was read as a single escape
producing byte 0xCD, eating the 'D'. The markers were never actually matching
the DSML text the model emits. Split each escape with adjacent string literal
concatenation so the byte sequence is exactly EF BD 9C 44 (｜D) at runtime.
Also adds <cstring> and <cstdio> includes (libstdc++ 13 does not transitively
expose std::strlen / std::snprintf via <string>).
The local plan file (uncommitted) was also updated with the same fixes so
Task 16's dsml_renderer.cpp does not re-introduce the bug.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): wire DsmlParser into Predict (ChatDelta)
Non-streaming Predict now emits one ChatDelta carrying content,
reasoning_content, and tool_calls[] parsed from the model's DSML output.
Reply.message still carries the raw model bytes for backends that prefer
the regex fallback path.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): wire DsmlParser into PredictStream
Per-token ChatDelta writes: content/reasoning_content go incrementally,
tool_calls emit TOOL_START as one delta (id + name) followed by
TOOL_ARGS deltas with incremental JSON. The Go-side aggregator
(pkg/functions/chat_deltas.go) reassembles them.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): chat template + reasoning_effort mapping
UseTokenizerTemplate=true + Messages -> ds4_chat_begin / append /
assistant_prefix. PredictOptions.Metadata['enable_thinking'] and
['reasoning_effort'] map to ds4_think_mode (DS4_THINK_HIGH default;
'max'/'xhigh' -> DS4_THINK_MAX; disabled -> DS4_THINK_NONE).
Tool-call rendering for assistant turns with tool_calls JSON arrives in
the next commit (dsml_renderer).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): render assistant tool_calls + tool results to DSML
Closes the round-trip: when an OpenAI client sends a multi-turn chat
where prior turns contain tool_calls or role=tool messages, build_prompt
serializes them back to the DSML shape the model was trained on. Mirrors
ds4_server.c's prompt renderer; uses nlohmann::json for parsing the
OpenAI tool_calls payload.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): disk KV cache module
Dir-based cache keyed by SHA1(rendered prompt prefix). File format:
'DS4G' magic + version + ctx_size + prefix_len + prefix + payload_bytes
+ ds4_session_save_payload output. NOT bit-compatible with ds4-server's
KVC files - that interop is a follow-up plan. LoadLongestPrefix walks
the dir picking the longest stored prefix that prefixes the incoming
prompt.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): wire KvCache into Predict/PredictStream
LoadModel reads 'kv_cache_dir' from ModelOptions.Options[], passes it to
g_kv_cache.SetDir. Each Predict/PredictStream computes a render text for
the request, tries LoadLongestPrefix to recover state, then Saves the
new state after generation. ds4_session_sync handles the live-cache
fast path internally, so the disk cache only matters for cold-starts
and cross-session reuse.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): add package.sh
Linux: bundles libc + ld + libstdc++ + libgomp + GPU runtime libs into
package/lib so the FROM scratch image boots without a host libc.
Darwin is handled by scripts/build/ds4-darwin.sh which uses otool -L.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(backend/cpp/ds4): rename namespace ds4_backend -> ds4cpp
ds4.h defines 'typedef enum {...} ds4_backend' which collides with our
C++ 'namespace ds4_backend' anywhere a TU includes both. kv_cache.h
includes ds4.h directly and surfaces the conflict immediately; other
TUs would hit it once gRPC dev headers are available.
Renames the C++ namespace to ds4cpp across all wrapper files and the
plan, leaving the upstream ds4 typedef untouched.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend): add Dockerfile.ds4
Single-stage builder (CUDA devel image for cublas, ubuntu:24.04 for cpu)
-> FROM scratch with packaged grpc-server + bundled runtime libs.
nlohmann-json3-dev is required for dsml_renderer's JSON handling.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(make): wire backend/cpp/ds4 + ds4-darwin into root Makefile
BACKEND_DS4 entry + generate-docker-build-target eval + docker-build-ds4
in docker-build-backends + .NOTPARALLEL guards. Also adds the
backends/ds4-darwin target which delegates to scripts/build/ds4-darwin.sh
(landed in Task 24).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: add backend-matrix entries for ds4 (cpu + cuda13, per-arch)
Two entries per build (amd64 + arm64) so backend-merge-jobs assembles a
multi-arch manifest. Skipping cuda12 - ds4 was validated against CUDA 13.
Darwin Metal is handled outside this matrix by backend_build_darwin.yml.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/index): add ds4 meta + image entries
cpu + cuda13 x latest + master. Darwin Metal builds publish under
ds4-darwin via the existing llama-cpp-darwin OCI pipeline.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(scripts/build): add ds4-darwin.sh
Native macOS/Metal build for the ds4 backend. Mirrors llama-cpp-darwin.sh:
make grpc-server -> otool -L for dylib bundling -> OCI tar that
'local-ai backends install' consumes via the backends/ds4-darwin
Makefile target.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci(darwin): build ds4-darwin in backend_build_darwin
Adds a 'Build ds4 backend (Darwin Metal)' step that runs the
backends/ds4-darwin Makefile target on the macOS runner.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(import): auto-detect ds4 weights via DS4Importer
Adds core/gallery/importers/ds4.go which matches on the antirez/deepseek-v4-gguf
repo URI and the DeepSeek-V4-Flash-*.gguf filename pattern. Registered before
LlamaCPPImporter so ds4 weights route to backend: ds4 instead of falling
through to llama-cpp.
Also lists ds4 in /backends/known so the /import-model UI surfaces it as a
manual choice for users who want to force the backend on a non-canonical URI.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(gallery): add deepseek-v4-flash-q2 (ds4 backend)
One-click install of the q2 weights with backend: ds4.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* docs(.agents): add ds4-backend.md
Documents the backend shape, DSML state machine, thinking-mode mapping,
disk KV cache, build matrix (cpu/cuda13/Darwin), and the BACKEND_BINARY
hardware-validation path.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(backend/cpp/ds4): pass UBUNTU_VERSION + arch env vars to install-base-deps
The .docker/install-base-deps.sh script needs UBUNTU_VERSION (defaults to
2404), TARGETARCH, SKIP_DRIVERS, and APT_MIRROR/APT_PORTS_MIRROR exported
into the environment so it can pick the right cuda-keyring / cudss / nvpl
debs and apt mirrors. Dockerfile.ds4 was declaring some of the ARGs but not
re-exporting them via ENV. Mirrors Dockerfile.llama-cpp's pattern.
Without this fix 'make docker-build-ds4 BUILD_TYPE=cublas CUDA_MAJOR_VERSION=13'
failed at:
/usr/local/sbin/install-base-deps: line 120: UBUNTU_VERSION: unbound variable
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/index): add Metal image entries for ds4
Adds metal-ds4 + metal-ds4-development image entries pointing at
quay.io/go-skynet/local-ai-backends:{latest,master}-metal-darwin-arm64-ds4
(built by scripts/build/ds4-darwin.sh on macOS arm64 runners), plus the
'metal' and 'metal-darwin-arm64' capability mappings on the ds4 meta and
ds4-development variant.
Closes a gap from the initial Task 23 landing - the Darwin Metal build
script and CI workflow step were already wired (Tasks 24-25), but the
gallery had no image entry for users to install the Metal variant.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(ci): use ubuntu:24.04 base for ds4 cuda13 matrix entries
The initial Task 22 matrix landing used base-image: 'nvidia/cuda:13.0.0-devel-ubuntu24.04'
which clashes with install-base-deps.sh's cuda-keyring step:
E: Conflicting values set for option Signed-By regarding source
https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/sbsa/
The canonical pattern (llama-cpp, ik-llama-cpp, turboquant) uses plain
'ubuntu:24.04' + 'skip-drivers: false' so install-base-deps installs CUDA
from scratch via its own keyring setup. Adopting that here.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(backend/cpp/ds4): drop install-base-deps.sh dependency
The .docker/install-base-deps.sh pipeline is built around the llama-cpp
needs: NVIDIA keyring + cuda-toolkit apt + gRPC-from-source build at
/opt/grpc. For ds4 we don't need any of that:
- CUDA: nvidia/cuda:13.0.0-devel-ubuntu24.04 ships /usr/local/cuda
ready to go; install-base-deps's keyring step then conflicts with
the pre-installed Signed-By.
- gRPC: ds4's grpc-server.cpp only links against grpc++; system
libgrpc++-dev (apt) is sufficient, no source build needed.
Replaced the install-base-deps invocation in Dockerfile.ds4 with a
direct 'apt-get install libgrpc++-dev libprotobuf-dev protobuf-compiler-grpc
nlohmann-json3-dev cmake build-essential pkg-config git'. Matrix entries
back to nvidia/cuda base + skip-drivers=true so install-base-deps would
no-op even if some downstream tooling calls it.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(backend/cpp/ds4): correct proto accessors + alias grpc::Status as GStatus
Two compile bugs caught by the docker build:
1. proto::Message uses snake_case accessors. The build_prompt loop called
m.toolcalls() / m.toolcallid() - the protoc-generated names are
m.tool_calls() / m.tool_call_id(). Plan-text bug propagated to the
wrapper.
2. The Status RPC method shadowed the 'using grpc::Status' alias, so any
later method declaration using Status as a return type failed to parse
('Status does not name a type' starting at LoadModel). Solution: alias
grpc::Status as GStatus instead, with no 'using' clause that would
conflict. All RPC method declarations and return-statement constructions
now use GStatus.
Pre-existing code reviewer flagged the Status-shadow concern as 'minor'
in the original Task 10 commit; it turned out to be a real compile blocker
under libstdc++ 13 once the surrounding methods were filled in.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(backend/cpp/ds4): preserve TOOL_ARGS content in dsml_parser Flush
When the model emitted a parameter value that arrived in the same buffer
as the surrounding tool_call markers (e.g. the buffered tail after a
literal '</think>' opened the model output), the parser deferred all
buffered bytes to Flush() because looks_like_prefix() always returns
true while buf starts with '<'. Flush() then drained the buffer as
plain CONTENT/REASONING regardless of parser state, so the bytes
between the parameter open and close markers were classified as
CONTENT instead of TOOL_ARGS.
Symptom: the model emitted
<|DSML|parameter name="location" string="true">Paris, France</|DSML|parameter>
and the assembled tool_call arguments came out as {"location":""} -
the opener and closer were emitted into the args stream but the
"Paris, France" content went to the assistant message instead.
Fix:
1. Flush() now uses the same state-aware emit logic as DrainPlain:
PARAM_VALUE bytes become TOOL_ARGS (json-escaped when string),
THINK bytes become REASONING, TEXT bytes become CONTENT, and
INVOKE / TOOL_CALLS structural whitespace is discarded.
2. looks_like_prefix() restricts its leading-'<' fallback to buffers
that have not yet seen a '>'. Without that change, char-by-char
feeds would discard the '<' of '<|DSML|invoke name="..."' once
the marker prefix length was reached but the closing quote/'>'
were still in flight.
Verified with a standalone harness that runs the failing input three
ways (single Feed, split-after-'>', and char-by-char) and aggregates
TOOL_ARGS for tool index 0: all three now produce
{"location":"Paris, France"}.
Assisted-by: Claude:opus-4.7 [Read,Edit,Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(backend/cpp/ds4): use ds4_session_sync + manual generation loop for KV persistence
ds4_engine_generate_argmax() is a self-contained helper that doesn't take or
update a ds4_session - it manages its own internal state. Our Predict and
PredictStream methods created g_session via ds4_session_create() but then
called ds4_engine_generate_argmax(), so g_session's KV state never advanced.
ds4_session_payload_bytes(g_session) returned 0 and the disk KV cache save
correctly rejected with 'session has no valid checkpoint to save'.
Switch both RPCs to the proper session API:
ds4_session_sync(g_session, &prompt, ...)
loop:
int token = ds4_session_argmax(g_session)
if token == eos: break
emit(token)
ds4_session_eval(g_session, token, ...)
After the loop the session has a real checkpoint and ds4_session_save_payload
writes the KV state to disk. Verified end-to-end on a DGX Spark GB10: three
.kv files (15-30 MB each) are written when BACKEND_TEST_OPTIONS sets
kv_cache_dir, and the e2e tool-call assertion still passes.
Also added stderr diagnostics to KvCache (enabled/disabled at SetDir; per-save
path + payload_bytes + result) so future failures are visible instead of
silent. The 'wrote ok' lines are low-volume - one per Predict/PredictStream
when the cache is enabled - and skipped entirely when the option is unset.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): use ds4_session_eval_speculative_argmax when MTP loaded
Wires MTP (Multi-Token Prediction) speculative decoding into the manual
generation loop in both Predict and PredictStream. When the upstream MTP
weights are loaded via 'mtp_path:' option AND we're on CUDA / Metal,
ds4_engine_mtp_draft_tokens() returns >0 and we switch the inner loop to
ds4_session_eval_speculative_argmax(), which can accept N>1 tokens per
verifier step. When MTP is not loaded (no option, CPU backend, or weights
absent), we fall through to the simple ds4_session_argmax + ds4_session_eval
path with no behavior change.
Validated on a DGX Spark GB10 with the optional MTP GGUF
(DeepSeek-V4-Flash-MTP-Q4K-Q8_0-F32.gguf, ~3.6 GB). LoadModel logs
'ds4: MTP support model loaded ... (draft=2)' on stderr.
Caveat per upstream README: 'currently provides at most a slight speedup,
not a meaningful generation-speed win'. Wired now mainly to track the
upstream API; bigger speedups arrive when ds4 improves the speculative path.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(backend/cpp/ds4): honor PredictOptions sampling with DSML-aware override
Mirrors ds4_server.c:7102-7115 sampling-policy semantics on the LocalAI
gRPC side. The generation loop now consults compute_sample_params() per
token to pick the effective (temperature, top_k, top_p, min_p), based on:
1. Request defaults: PredictOptions.temperature / .topk / .topp / .minp
2. Thinking-mode override: when enable_thinking != false, force T=1.0,
top_k=0, top_p=1.0, min_p=0.0 (creativity for the reasoning pass and
the trailing content)
3. DSML structural override: when DsmlParser::IsInDsmlStructural()
returns true (we are between tool-call markers but NOT in a param
value payload), force T=0.0 so protocol bytes parse cleanly
When the effective temperature is 0, we keep using ds4_session_argmax +
MTP speculative path (matches ds4-server's gate that only enables MTP for
greedy positions). When > 0, we call ds4_session_sample(s, T, ...) with
a per-thread RNG seeded from system_clock and fall back to single-token
ds4_session_eval.
New public method on DsmlParser: IsInDsmlStructural() encodes which states
need protocol-byte determinism. PARAM_VALUE is excluded (payload uses user
sampling); TEXT and THINK are excluded (no tool-call context to protect).
Verified on the DGX Spark GB10: the e2e suite still passes with all 5
specs including tools, and the Predict output now varies between runs
(creative sampling active) while the tool-call args remain a clean
'{"location":"Paris, France"}' because the parser-state check forces
greedy on the structural bytes.
UX note: thinking mode is ON by default (matching ds4-server). Users who
want deterministic output should set Metadata.enable_thinking = false.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(gallery): add sha256 to deepseek-v4-flash-q2 entry
Per HF LFS metadata for antirez/deepseek-v4-gguf:
size: 86720111200 bytes (~80.76 GiB)
sha256: 31598c67c8b8744d3bcebcd19aa62253c6dc43cef3b8adf9f593656c9e86fd8c
LocalAI's downloader verifies sha256 when present, so users who install
deepseek-v4-flash-q2 from the gallery get integrity-checked weights and
the partial-download issue (an 81 GB file is easy to truncate) becomes
recoverable instead of silently producing a broken backend.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* test(whisper): wire e2e streaming transcription target
Adds test-extra-backend-whisper-transcription, mirroring the existing
llama-cpp / sherpa-onnx / vibevoice-cpp targets. The generic
AudioTranscriptionStream spec at tests/e2e-backends/backend_test.go:644
fails today because backend/go/whisper has no streaming impl - this
target is the failing TDD gate that the next phase makes pass.
Confirmed RED locally: 3 Passed (health, load, offline transcription),
1 Failed (streaming spec hits its 300s context deadline because the
base implementation returns 'unimplemented' but doesn't close the
result channel, leaving the gRPC stream open until the client times
out).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(whisper-cpp): expose new_segment_callback to the Go side
Adds set_new_segment_callback() and a C-side trampoline that whisper.cpp
invokes once per new text segment during whisper_full(). The trampoline
dispatches (idx_first, n_new, user_data) to a Go function pointer
registered via purego.NewCallback - text and timings are pulled by Go
through the existing get_segment_text/get_segment_t0/get_segment_t1
getters.
Wires the hook only when streaming is actually requested, to avoid a
per-segment function-pointer dispatch on the offline path.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(whisper-cpp): implement AudioTranscriptionStream
Wires whisper.cpp's new_segment_callback through purego back to Go so
the streaming transcription RPC produces real, time-correlated deltas
while whisper_full() is still decoding. Each segment becomes one
TranscriptStreamResponse{Delta}; whisper_full's return is the
TranscriptStreamResponse{FinalResult} carrying the full segment list,
language, and duration.
Per-call state is tracked in a sync.Map keyed by an atomic counter; the
Go callback registered via purego.NewCallback is a singleton, dispatched
through user_data. SingleThread today means only one entry is ever live,
but the map shape matches the sherpa-onnx TTS callback pattern.
The streaming path's final.Text is the literal concat of every emitted
delta (a strings.Builder accumulated by onNewSegment) so the e2e
invariant `final.Text == concat(deltas)` holds exactly. The first delta
has no leading space; subsequent deltas are space-prefixed. The offline
AudioTranscription path is unchanged.
Closes the gap with sherpa-onnx, vibevoice-cpp, llama-cpp, and tinygrad,
which already implement AudioTranscriptionStream.
Verified GREEN locally: make test-extra-backend-whisper-transcription
passes 4/4 specs (3 Passed initially under RED, +1 streaming spec now).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(whisper-cpp): assert progressive multi-segment streaming
Drives AudioTranscriptionStream against a real long-audio fixture and
asserts len(deltas) >= 2. The generic e2e spec at
tests/e2e-backends/backend_test.go:644 only checks len(deltas) >= 1
which is satisfied by both real and faked streaming - this spec is the
guardrail that a future "fake" impl can't sneak past.
Skipped by default (env-gated, like the cancellation spec); set
WHISPER_LIBRARY, WHISPER_MODEL_PATH, and WHISPER_AUDIO_PATH to a 30+
second clip to run.
Verified locally with a 55s 5x-JFK concat against ggml-base.en.bin:
1 Passed in 7.3s, deltas >= 2, finalSegmentCount >= 2,
concat(deltas) == final.Text.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci(whisper-cpp): add transcription gRPC e2e job
Mirrors tests-sherpa-onnx-grpc-transcription /
tests-llama-cpp-grpc-transcription. Runs make
test-extra-backend-whisper-transcription whenever the whisper backend
or the run-all switch fires, so a pin-bump or refactor that breaks
streaming transcription gets caught before merge.
The whisper output on detect-changes is already emitted by
scripts/changed-backends.js (it iterates allBackendPaths); this PR
just exposes it as a workflow output and consumes it.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(whisper-cpp): silence errcheck on AudioTranscriptionStream defers
golangci-lint runs with new-from-merge-base=origin/master, so the
identical defer patterns in the existing offline AudioTranscription
path are grandfathered while the new ones in AudioTranscriptionStream
trip errcheck. Wrap both defers in `func() { _ = ... }()` to match what
errcheck wants without altering behavior. The errors from os.RemoveAll
and *os.File.Close are not actionable inside a defer here (we're
already returning), matching the offline path's contract.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* ci(backend_build): plumb builder-base-image and BUILDER_TARGET build-args
Adds an optional builder-base-image input. When set, BUILDER_BASE_IMAGE
is forwarded as a build-arg AND BUILDER_TARGET=builder-prebuilt is set
to select the variant Dockerfile's prebuilt-base stage. When empty,
BUILDER_TARGET=builder-fromsource (the default) keeps the existing
from-source build path.
This makes the prebuilt-base optimization opt-in per matrix entry
without breaking local `make backends/<name>` invocations or backends
whose Dockerfile doesn't have a prebuilt path.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci(llama-cpp,ik-llama-cpp,turboquant): multi-target Dockerfiles for prebuilt + from-source
Restructure the three llama.cpp-derived Dockerfiles so each supports
two builder paths in a single file, selected via the BUILDER_TARGET
build-arg:
BUILDER_TARGET=builder-fromsource (default)
- Standalone build: gRPC stage + apt installs + (conditionally)
CUDA/ROCm/Vulkan + compile.
- Used by `make backends/llama-cpp` locally and any caller that
doesn't supply a prebuilt base.
BUILDER_TARGET=builder-prebuilt
- FROM \${BUILDER_BASE_IMAGE} (one of quay.io/go-skynet/ci-cache:
base-grpc-* shipped in PR #9737).
- Skips ~25-35 min of gRPC compile + ~5-10 min of toolchain installs.
- Used by CI when the matrix entry sets builder-base-image.
Final FROM scratch resolves BUILDER_TARGET via an aliasing FROM stage
(BuildKit doesn't support variable expansion directly in COPY --from),
then COPY --from=builder pulls package output from the chosen path.
BuildKit prunes the unreferenced builder, so each build only does the
work for the chosen path.
The compile RUN is identical between both builder stages, so it's
factored into .docker/<name>-compile.sh and bind-mounted into both.
ccache mount + cache-id stay per-arch / per-build-type.
Local DX preserved: `make backends/llama-cpp` (no extra args) defaults
to BUILDER_TARGET=builder-fromsource and works exactly as before.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci(backend.yml,backend_pr.yml): forward builder-base-image from matrix
Plumbs the new optional builder-base-image input from matrix into
backend_build.yml. backend_build.yml derives BUILDER_TARGET from
whether builder-base-image is set, so matrix entries that map to a
prebuilt base get the prebuilt path; entries that don't (python/go/
rust backends) fall through to the default builder-fromsource (which
their own Dockerfiles don't reference, so it's a no-op for them).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci(backend-matrix): wire builder-base-image to llama-cpp variants
For every entry whose Dockerfile is llama-cpp/ik-llama-cpp/turboquant,
add a builder-base-image field pointing at the appropriate prebuilt
quay.io/go-skynet/ci-cache:base-grpc-* tag.
backend_build.yml derives BUILDER_TARGET from this field's presence:
non-empty -> builder-prebuilt; empty -> builder-fromsource. So this
commit alone activates the prebuilt-base path for these 23 backends
in CI, while local `make backends/<name>` (no extra args) keeps the
from-source path.
Mapping by (build-type, arch):
- '' / amd64 -> base-grpc-amd64
- '' / arm64 -> base-grpc-arm64
- cublas-12 / amd64 -> base-grpc-cuda-12-amd64
- cublas-13 / amd64 -> base-grpc-cuda-13-amd64
- cublas-13 / arm64 -> base-grpc-cuda-13-arm64
- hipblas / amd64 -> base-grpc-rocm-amd64
- vulkan / amd64 -> base-grpc-vulkan-amd64
- vulkan / arm64 -> base-grpc-vulkan-arm64
- sycl_* / amd64 -> base-grpc-intel-amd64
- cublas-12 + JetPack r36.4.0 / arm64 -> base-grpc-l4t-cuda-12-arm64
Cold-build savings expected: ~25-35 min per variant (skips the gRPC
compile + toolchain install that's now in the base).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: add base-grpc-l4t-cuda-12-arm64 variant for legacy JetPack entries
Two matrix entries (-nvidia-l4t-arm64-llama-cpp, -nvidia-l4t-arm64-
turboquant) build against nvcr.io/nvidia/l4t-jetpack:r36.4.0 + CUDA
12 ARM64. They're distinct from -nvidia-l4t-cuda-13-arm64-* which use
Ubuntu 24.04 + CUDA 13 sbsa. Add the missing JetPack-based variant
to base-images.yml so those two entries' builder-base-image mapping
in the previous commit resolves.
Bootstrap order before merging this PR (re-run base-images.yml on
this branch — 9 existing variants hit BuildKit cache, only the new
l4t-cuda-12-arm64 builds cold):
gh workflow run base-images.yml --ref ci/base-images-consumers
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci: extract base-builder install logic into .docker/install-base-deps.sh
Pre-extraction, the apt + protoc + cmake + conditional CUDA/ROCm/Vulkan
+ gRPC install logic was duplicated across four files:
- backend/Dockerfile.base-grpc-builder (CI prebuilt-base source of truth)
- backend/Dockerfile.llama-cpp (builder-fromsource stage)
- backend/Dockerfile.ik-llama-cpp (builder-fromsource stage)
- backend/Dockerfile.turboquant (builder-fromsource stage)
A bump to e.g. CUDA toolkit packages had to be made in 4 places, and
drift between the prebuilt base and the variant-Dockerfile from-source
path was a real concern (ik-llama-cpp's hipblas branch was already
missing the rocBLAS Kernels echo that llama-cpp / turboquant /
base-grpc-builder all had).
Factor the install logic into a single .docker/install-base-deps.sh
that reads its inputs from env vars and runs conditionally on
BUILD_TYPE / CUDA_*_VERSION / TARGETARCH. Each Dockerfile now bind-
mounts the script alongside .docker/apt-mirror.sh and invokes it from
a single RUN step.
The variant Dockerfiles' grpc-source stage is removed entirely — the
script handles gRPC compile + install at /opt/grpc, and the
builder-fromsource stage mirrors builder-prebuilt by copying
/opt/grpc/. to /usr/local/.
Result:
- install-base-deps.sh: 244 lines (one source of truth)
- Dockerfile.base-grpc-builder: 268 -> 98 lines
- Dockerfile.llama-cpp: 361 -> 157 lines
- Dockerfile.ik-llama-cpp: 348 -> 151 lines
- Dockerfile.turboquant: 355 -> 154 lines
- Total Dockerfile bytes: 1332 -> 560 lines (58% reduction)
Bit-equivalence between prebuilt and from-source paths is now enforced
by construction: both invoke the same script with the same inputs.
A side-effect is that ik-llama-cpp now also gets the rocBLAS Kernels
echo + clblas block parity it was previously missing.
Includes the BUILD_TYPE=clblas branch (libclblast-dev) for parity even
though no current CI matrix entry uses it.
After this commit's force-push, base-images.yml needs to be redispatched
on this branch — the Dockerfile.base-grpc-builder content shifts so the
existing cache won't apply for the install layer (gRPC layer also
rebuilds since it's now in the same RUN step).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* ci(base-images): skip-drivers on JetPack l4t variant
cuda-nvcc-12-0 isn't installable via apt on the JetPack r36.4.0 base
image — JetPack ships CUDA preinstalled at /usr/local/cuda and its
apt feed doesn't carry the cuda-nvcc-* packages from the public
repositories. The original matrix entry for -nvidia-l4t-arm64-llama-cpp
on master sets skip-drivers: 'true' for exactly this reason; the
new base-grpc-l4t-cuda-12-arm64 base needs to match.
Also forwards SKIP_DRIVERS as a build-arg from matrix into the build
(was missing entirely before this commit).
Caught by run 25612030775 — l4t-cuda-12-arm64 failed at:
E: Package 'cuda-nvcc-12-0' has no installation candidate
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Introduces a parameterized Dockerfile.base-grpc-builder that produces
a fully-prepped builder base image (apt deps + protoc + cmake + gRPC
at /opt/grpc + conditional CUDA/ROCm/Vulkan toolchains) and a
base-images.yml workflow that builds + pushes 9 variants to
quay.io/go-skynet/ci-cache:base-grpc-*:
base-grpc-amd64 (Ubuntu 24.04, CPU-only)
base-grpc-arm64 (Ubuntu 24.04, CPU-only)
base-grpc-cuda-12-amd64 (Ubuntu 24.04 + CUDA 12.8)
base-grpc-cuda-13-amd64 (Ubuntu 22.04 + CUDA 13.0)
base-grpc-cuda-13-arm64 (Ubuntu 24.04 + CUDA 13.0 sbsa)
base-grpc-rocm-amd64 (rocm/dev-ubuntu-24.04:7.2.1 + hipblas)
base-grpc-vulkan-amd64 (Ubuntu 24.04 + Vulkan SDK 1.4.335)
base-grpc-vulkan-arm64 (Ubuntu 24.04 + Vulkan SDK ARM 1.4.335)
base-grpc-intel-amd64 (intel/oneapi-basekit:2025.3.2)
The variant Dockerfiles (Dockerfile.llama-cpp, ik-llama-cpp, turboquant)
are NOT touched in this PR. PR 2 will refactor them to FROM these
prebuilt bases. This PR is intentionally inert - landing it changes no
existing CI behavior. The base images don't exist on quay until
someone manually triggers the workflow.
Bootstrap after merge:
gh workflow run base-images.yml --ref master
Wait ~30 min for all 9 variants to push, then merge PR 2 (the
consumer-side refactor that uses BUILDER_BASE_IMAGE build-arg to
FROM these tags).
Triggers afterwards:
- Saturdays 05:00 UTC (cron) - picks up upstream security updates,
runs ~24h before the backend.yml Sunday cron so bases are fresh.
- workflow_dispatch - manual ad-hoc rebuild.
- master push touching Dockerfile.base-grpc-builder or this workflow.
Why split into two PRs: the variant Dockerfiles in PR 2 will FROM the
prebuilt bases and have no from-source fallback. Their CI builds fail
if the bases don't exist on quay yet. Landing infrastructure first +
manual bootstrap + then consumer refactor avoids a broken-master window.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Mirror the ccache mount added to Dockerfile.llama-cpp in 9228e5b4 for
the other two llama.cpp-derived backends. Same shape, distinct mount
ids so each backend's cache is independent:
ik-llama-cpp-ccache-${TARGETARCH}-${BUILD_TYPE}
turboquant-ccache-${TARGETARCH}-${BUILD_TYPE}
ik_llama.cpp is a different upstream fork; no source overlap with
llama-cpp, separate cache makes sense.
turboquant is a llama.cpp fork that reuses backend/cpp/llama-cpp
source via a thin wrapper Makefile — most TUs would in principle hit
llama-cpp's ccache too. Keeping them separate for now to avoid one
fork's regressions poisoning the other; revisit sharing after we have
hit-rate numbers.
Same registry-export behavior as llama-cpp: the cache mount rides on
backend_build.yml's existing cache-to: type=registry,mode=max.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The big RUN at line 268 of Dockerfile.llama-cpp re-runs from scratch on
every LLAMA_VERSION bump (or any LocalAI source change due to
COPY . /LocalAI just before). For CUDA-13 specifically that compile
recently hit the GHA 6h hard limit and failed:
https://github.com/mudler/LocalAI/actions/runs/25598418931/job/75148244557
Add a BuildKit cache mount on /root/.ccache and thread ccache through
CMake (CMAKE_C/CXX/CUDA_COMPILER_LAUNCHER) so most translation units
hit cache when their preprocessed source is byte-identical to the
previous build.
The cache mount is exported to the registry as part of the existing
cache-to: type=registry,mode=max in backend_build.yml, so it persists
across runs. mount id is keyed on TARGETARCH + BUILD_TYPE so different
variants don't thrash the same cache slot; sharing=locked serializes
concurrent writes.
Cold-build effect (first run after enable, or on LLAMA_VERSION bump
that touches every TU): unchanged. Hot-build effect (subsequent runs
with the same source, or LLAMA_VERSION bumps that touch a handful of
files): ~5-15 min for the llama.cpp compile vs the previous 1-3h cold.
For CUDA-13 specifically this should bring rebuilds well under the 6h
GHA limit.
Does NOT help the *first* post-bump build — that's still cold. For
that, follow-up work would be: (a) trim CUDA_DOCKER_ARCH to modern
GPUs only, (b) audit which CMake variants the published images
actually need, (c) pre-built CUDA+gRPC base image.
ccache package is already installed in the builder stage (line 90).
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The PR that introduced the per-arch + manifest-merge pilot (#9727)
only touched CI infrastructure files, so the path filter correctly
skipped backend builds on its merge commit. To observe the new
backend-merge-jobs flow assemble a real manifest list, this commit
touches faster-whisper's Makefile so its two new per-arch entries
schedule and the merge job runs.
The trailing comment is the smallest possible diff and is harmless
to the build.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
