mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-16 08:18:29 -04:00
3f4e446adcdb517543c62d5f8e09ef7cdb5a14f5
261
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
47097041ff |
fix(vllm): apply Options[] engine flags before engine init (#11147)
fix(vllm): apply Options[] engine flags before engine init (#11130) CLI-style flags in a model's `options:` array (`--quantization:gptq_marlin`, `--enable-prefix-caching`, `--kv-cache-dtype:fp8_e5m2`) were discarded: the backend only ever read `tool_parser`/`reasoning_parser` out of Options[], and did so *after* `AsyncLLMEngine.from_engine_args()`, where nothing it set could still reach the engine. Map `--` prefixed options onto the AsyncEngineArgs dataclass before the engine is constructed. Names are normalized the way vLLM's CLI spells them (`--enable-prefix-caching` -> `enable_prefix_caching`), values are coerced to the target field's type (bare flag -> True for booleans), and unknown or uncoercible flags warn and are skipped instead of failing the load, since Options[] is a bag shared with backend-level settings. Field types come from the annotation's base so `Literal["auto", "float16"]` (vLLM's dtype) is not mistaken for a float. Precedence is typed proto fields -> `options:` -> `engine_args:`. The production engine_args defaults seeded in hooks_vllm.go therefore skip any key the user already set as an option, otherwise the later engine_args pass would silently override it. Parser lookups now accept both spellings, so `--reasoning-parser:qwen3` selects LocalAI's parser as well. The helper's tests are stdlib-only and run in the lint workflow's dependency-light job via `make test-python-helpers`. Assisted-by: Claude:claude-opus-5 golangci-lint Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: localai-org-maint-bot <bot-opensource@localaisrl.com> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
9c85cacfe3 |
feat(audio-cpp): add the audio.cpp native backend (#11141)
* backend(audio-cpp): add the native build scaffold Links 0xShug0/audio.cpp engine_runtime through its public framework headers and serves Health/Status. Model loading and the audio RPCs follow. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): keep the build-tree rpath at $ORIGIN Upstream sets CMAKE_BUILD_WITH_INSTALL_RPATH in its own directory scope, so CMake was appending its build-tree library dir to our target and baking an absolute build-host path into the shipped binary. Set BUILD_WITH_INSTALL_RPATH on the target so a package that forgets to bundle libggml*.so fails on the build machine too, instead of only on a user's box. Also document why EXCLUDE_FROM_ALL must stay on the add_subdirectory call, correct the claim that Ubuntu ships no gRPC CMake config, stop the pin comment from repeating the assignment token that bump_deps.sh rewrites, and make test-engine fail rather than pass when no test is registered. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): parse namespaced model options Splits option entries on the first colon so path values survive, and routes load./session. prefixes to the upstream load and session option maps. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): reject out-of-range numeric model options std::atoi is undefined once the digits exceed long and in practice wraps, so device:2147483648 was accepted and handed the ggml backend selector a device index of -2147483648 from a function whose error text promises a non-negative integer. Parse with strtol and reject on ERANGE, on a value above INT_MAX, and on any unconsumed trailing input. The error strings are unchanged. Name the whole entry in the unknown-key error too: an entry like ':value' has an empty key and left the user nothing to grep for in their YAML. Tests look keys up through a helper instead of map::at, so a prefix off-by-one fails one named check rather than aborting the binary and skipping the rest of the suite, and cover the overflow, negative and non-numeric paths. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): route LocalAI RPCs onto audio.cpp tasks Task-major resolution over the family's advertised capability set, with the voice-reference and instructions signals selecting cloning and voice design, and a streaming-to-offline fallback for server-streaming transcription only. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): use upstream's 'spk' task name and pin the preference order The SpeakerRecognition short name was 'spkrec', which audio.cpp neither prints nor parses; a name copied out of audio.cpp was rejected and a pinned 'spkrec' would not survive the engine boundary. Emit 'spk', keep 'spkrec' as an input-only alias, and correct the known-tasks lists. Three assertions were vacuous because their fixtures advertised a single task, so reversing a preference order or dropping the RPC name and the attempted pairs from the capability error all passed. Give them fixtures that can tell the orderings apart. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): convert sample, time and PCM units Integer nanosecond conversion so 44.1 kHz stays exact, float seconds for the VAD and diarization messages, and saturating s16le encode so an overshooting sample cannot wrap to the opposite sign. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): harden seconds_to_samples against NaN and overflow seconds_to_samples is the one entry point fed by untrusted-shaped input: a float-seconds timestamp off the wire, or a boundary from a model that diverged. Its guard covered only the low side, so NaN and out-of-range values fell through to an undefined double-to-int64 cast and came back as INT64_MIN. A hugely negative sample index used later as an offset or a length is a wild pointer rather than merely a wrong timestamp. Reject NaN with the !(x > 0) form and saturate before the cast. Also round instead of truncating there. These functions exist to cross the float seconds boundary the VAD and diarize messages use, and truncation lost a sample about half the time on the samples-to-seconds-and-back round trip, starting at n=1. Pin the decode scale at INT16_MIN, pin nanosecond truncation on a nonzero fraction, and record why the clamp argument order in f32_to_s16le is load-bearing for NaN. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): map NaN PCM samples to silence explicitly f32_to_s16le relied on std::min argument order to keep a NaN sample away from std::lround, whose result is unspecified for NaN. That was too subtle to rest on a comment, and the comment was itself wrong: it warned against a spelling that the outer std::max already catches, while three real spellings leak, including std::clamp, which is the idiomatic C++17 way to write the same clamp and so the likeliest future edit. Divert NaN before the clamp and encode it as 0. A NaN sample rendered as a full-scale click is worse audio than a dropped one, and this unit converts audio that may have originated off the wire. Pin it with an exact-value check rather than a range check, since all three outcomes the plausible spellings produce are finite and inside full scale, plus an invalid-operation check that fails unless the NaN is diverted before any ordered comparison. That second check is what catches modernizing the clamp and dropping the guard together. Also bound the seconds round-trip comment, which claimed unconditionally what holds only below roughly 2^23 samples, and document NaN, saturation and that bound in the header. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): assemble transcripts from runtime spans The top-level transcript text is TaskResult.text_output verbatim. audio.cpp carries text nowhere else: speech_segments, speaker_turns and word_timestamps hold spans and labels only, so deriving the text from them empties the transcript for any producer that omits word timing, VibeVoice diarized ASR included. Fixtures cover every observed producer shape. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): keep a nested speaker turn's own label A segment sourced from speaker_turns re-derived its speaker by greatest overlap. A turn's overlap with its own span is the largest possible, so a turn nested inside another speaker's turn could only tie with the container, and the tie went to whichever came first. sortformer_diar binarizes each speaker independently and sorts by start sample, so the container always comes first and the interjecting speaker was silently erased from DiarizeSegment.speaker. choose_segment_spans now carries the label out with the span. Also pins the nearest-segment fallback against measuring from either endpoint or from segment position, which a trailing-only stray word could not do, and exercises the empty-word guard in join_words. Two fixtures that pin a rule but do not mirror any pinned family are relabelled defensive. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serialize runs with a wedge-aware guard audio.cpp sessions are not reentrant and a wedged CUDA call cannot be cancelled, so a plain mutex would pile every worker thread behind a stuck GPU. Callers waiting past the configured bound, or arriving while the holder has already overrun it, fail fast instead. A caller that queues behind a healthy run deliberately does not stamp the clock: only the thread that takes the lock does. Stamping on arrival would restart the wedge clock on every request and hide a stuck run from everyone behind it, which is the pile-up this guard exists to prevent. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serialize inference through an InferenceLane One audio.cpp model is loaded per backend process and its sessions are not reentrant, so concurrent gRPC handlers have to take turns. Serialization alone is not enough: a wedged GPU call cannot be cancelled from userspace, so an unbounded queue behind one stuck run would swallow every gRPC worker thread until the process is useless. InferenceLane gives handlers a lane with room for one runner. LaneEntry occupies it for a scope and gives it back on every exit, including an exception, and is the only way to take the lane at all: occupy/vacate are private with LaneEntry as the sole friend, so a caller cannot acquire without holding something that releases. LaneEntry is immovable on purpose, because a moved-from entry would have to stop releasing while the lane still recorded it as occupied. A caller either waits indefinitely or brings a millisecond budget. A bounded caller that cannot get in fails instead of waiting on, and a bounded caller whose budget is already shorter than the age of the run in the lane fails immediately, which is what stops a queue forming behind a wedged run. The two failures carry different text: one names the wait it exhausted, the other states the measured age of the run without claiming to know why it is long, since a short budget meeting a legitimately long run lands there too. The run's age is stamped only after acquisition. A waiter that published itself as holder would restart the measurement and hide a genuinely stuck holder from every caller behind it. Budget negotiation and the overrun decision are pure functions taking their inputs explicitly, so both are covered without threads or sleeping. The per-model ceiling arrives as an int of milliseconds; a request may tighten it and may never loosen it. Replaces the previous run_guard unit, which was a derivative of an Apache-2.0 file upstream and could not stay in an MIT tree. Written from a behaviour contract with no reference to the removed code. Tests: 65 checks, standard library only, single translation unit, clean under -Wall -Wextra. Mutation tested at 23/23 killed; two of those mutants exposed missing coverage and the tests were extended until they died. ThreadSanitizer clean. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): make the B10 test able to fail, and document LaneEntry Review of the previous commit found the B10 test could not fail for the reason it was named. It aged the in-flight run to about 120 ms and then tried two budgets, 30 ms and 60 ms, both under that age, so both callers took the fail-fast path. "The two failure modes do not share one message" was comparing two fail-fast messages that differ only in the budget they print, and the timeout path was never reached. The second budget is now 400 ms, well over the run's age, so that caller queues and times out, and a new check asserts which path each caller took instead of inferring it from inequality. A mutant that makes the fail-fast path emit the timeout message previously died only on B4 and B8 checks; it now also dies on B10. Comment-only changes elsewhere. LaneEntry now says it is not reentrant and does not detect reentrancy: a second entry on a thread that already holds the lane surfaces as LaneUnavailable with a positive budget, but parks silently in unbounded mode, which matters because a handler may hold one across a whole stream. The immovability note now names the shapes that work, an optional emplaced in place or a unique_ptr, rather than saying to hold the entry indirectly without saying how; all three documented forms were compiled before being written down, which is how the note came to say that an optional of an immovable type cannot itself be returned. The header's explanation of why fail-fast exists is reworded. Two clauses traced back to a specification written after reading the Apache-2.0 upstream header, and while that was judged de minimis, this unit was rewritten precisely to carry no upstream expression at all. The margin table in the report was also wrong about which wall-clock margins are load-sensitive: there are four, not one, and the tightest is the B3 arrival check, which is now flagged at the call site. No margin value changed and none moved across 65 runs. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): gate model loading on the audio.cpp family Refuses any GGUF without an audiocpp.model_spec.family key and any non-GGUF path without an explicit family option, so the model loader's greedy backend probe cannot bind an unrelated llama.cpp GGUF to this backend (#9287). Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): load models and cache sessions per task Loads one ILoadedVoiceModel and creates an IVoiceTaskSession lazily per (task, mode), so the same model serves both the unary and streaming RPCs. LoadModel derives the family from GGUF metadata or an explicit option and fails with INVALID_ARGUMENT otherwise, so a failed load is a gRPC error the backend probe can see. audiocpp_backend::Task mirrors engine::runtime::VoiceTaskKind positionally, and drift there is silent: every unit still compiles and every test still passes while the backend runs a different task. Two mechanisms pin it. The static_asserts in loaded_model.cpp catch an insertion or a reorder, and -Werror=switch on that one file turns an appended upstream enumerator into a build failure rather than a warning in a 600 file log. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): stop aborting the process on SIGTERM The signal handler called grpc::Server::Shutdown directly. Shutdown takes an absl::Mutex, which is not async-signal-safe: the handler can interrupt a thread already holding that mutex, and abseil's deadlock detector responds by aborting. Every SIGTERM therefore ended in exit 134 and a 'dying due to potential deadlock' stack rather than a drained shutdown. The handler now sets a lock-free atomic and returns. Server::Wait moves to a helper thread so the main thread can poll that flag and call Shutdown itself, outside any signal context. A condition variable would not have helped, because notifying one from a handler is not async-signal-safe either. SIGTERM and SIGINT both exit 0 with no stack trace, where both previously exited 134. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): correct the status, lifetime and state contracts of LoadedModel An environment fault during session creation was reported as UNIMPLEMENTED. A missing libggml-cpu-*.so surfaced to the client as 'family silero_vad advertises vad/offline but refused to create the session: Failed to initialize CPU backend', which tells LocalAI the model cannot do this and must never be retried, and sends an operator hunting a capability bug instead of a packaging one. A throw from create_task_session is now a plain runtime_error, so it maps to INTERNAL. Only a null return, where the family genuinely declined, stays a CapabilityError. The model.'s task: option was parsed and then dropped: it lived in a local that died at the end of LoadModel and had no route to RequestShape::pinned_task. LoadedModel now keeps it and exposes pinned_task(). The global model becomes a shared_ptr reached through snapshot(). An audio RPC runs for seconds and cannot hold g_model_mu for its duration, so under a unique_ptr a Free arriving mid-request would destroy the model underneath it. Handlers now take a counted reference and whichever finishes last does the teardown, outside the lock. session_for documents the streaming state contract rather than resetting the session itself. Resetting on a cache hit was tried first and is not possible: silero_vad throws 'session prepare() must be called before Silero VAD reset()', so it would turn an ordinary second fetch into a hard error. start_stream's base implementation is already a reset, so a caller that runs prepare then start_stream per stream gets a clean session; a probe against the bundled silero_vad confirms an identical replay when it does and a carried-over stream when it does not. Also: an unknown backend: name is rejected before the model loads rather than after; MainGPU is parsed instead of passed through std::atoi, which turned 'gpu1' into device 0 silently; and device carries a device_set flag, because 0 is both the default and a real device index, so MainGPU was overriding an explicit device:0 that the neighbouring threads: handling promises will win. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serve the VAD and Diarize RPCs Both emit float seconds, converted from the runtime's sample-index spans, and both take a counted reference to the loaded model through snapshot() and hold it for the whole call: a Free arriving mid-request drops only the global's reference, so whichever request finishes last destroys the model instead of one of them running on freed weights. An AddressSanitizer build reproduces exactly that heap-use-after-free inside ggml_vec_dot_f32 when the handler keeps a raw pointer instead, which is why the shape is what it is. The inference lane is taken before session_for, not after. session_for reads and writes an unsynchronised session cache and the offline run calls prepare(), which mutates the session, so both belong inside the lane. Diarize routes before it reads the input file, so a family that cannot diarize at all says so rather than complaining about the audio first. Its per-segment text stays empty because audio.cpp's SpeakerTurn carries a span and a speaker label only, and nested or overlapping turns are passed through untouched: a sortformer turn inside another speaker's turn is correct output for overlapped speech, and LocalAI is overlap-tolerant downstream. Duration counts frames rather than floats, so a stereo input does not report twice its length. Verified end to end against upstream's bundled silero_vad, which needs no download, using the bundled 16 kHz speech asset: a synthetic tone returns nothing, correctly, because silero detects speech and a sine is not speech. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): enforce ModelIdentity on VAD and Diarize audio-cpp was the only C++ backend without the model-identity guard, and no later task in the plan added it. pkg/grpc/server.go enforces checkModelIdentity on exactly these two RPCs, for the reason #10952 records: in distributed mode a worker can recycle a stopped backend's gRPC port for another model's backend, and the controller's liveness-only probe cannot tell a stale cached route from a live one. Without this guard a stale route gets a different model's VAD or diarization answer back with a 200. The loaded identity lives on LoadedModel rather than in a separate global, which is where this differs from llama-cpp. A handler holding the model through snapshot() then necessarily judges against the identity that model was loaded with, and a concurrent reload cannot swap one without the other. The refusal is NOT_FOUND carrying the verbatim grpcerrors.ModelMismatchSentinel substring. session_for and run_offline now take a const LaneEntry & proof-of-holding parameter. The rule that both must run under the inference lane was prose, which is exactly how the plan came to specify the inverted order; it is now a compile error. Restoring the inverted order fails to build rather than racing on an unsynchronised session map with a mutating prepare(). Diarize's speaker-hint comment claimed the dropped hints were "not a silent failure". From the caller's side that is what they are, and backend.proto documents num_speakers as forcing, so the comment now says plainly that the forwarding is dead for sortformer and that the family which lands must either honour num_speakers or refuse it. read_audio_file inspects the error_code from exists(), so an unsearchable parent directory no longer reports as a missing file. The VAD handler records the stimulus that actually works, since silero correctly ignores synthetic tones and the next task would otherwise rediscover that. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): make the lane and identity guards structural Two hardenings ahead of the eleven handlers still to be written, both of which get harder to retrofit later. The lane proof-of-holding parameter was a const reference, which binds to a temporary, so session_for(rpc, shape, model->acquire(0)) compiled. Each such temporary dies at the end of its own full-expression, releasing the lane between two calls that must share one: precisely the split the parameter exists to prevent, and the form a future author is most likely to reach for because it reads as tidy. A non-const reference requires an lvalue, so the temporary form now fails to compile while the named-local handlers build unchanged. The header comment no longer implies the check is total either: it proves a lane was taken, not that it is this model's lane. The identity check was two lines each handler had to remember, with nothing failing if a new one forgot them and no C++ equivalent of model_identity_modalities_test.go to notice. snapshot() becomes snapshot_unchecked(), whose only legitimate caller is Status, since HealthMessage carries no ModelIdentity. Handlers go through snapshot_for(), which takes the counted reference, refuses when nothing is loaded, and runs the identity check before anything can route. Every handler already has to call something to obtain the model, so the guarded call is now the shortest path and skipping it means deliberately typing snapshot_unchecked. A convention that has to be remembered can rot; this cannot. Verified: the temporary-argument and inverted-order forms each fail to compile with the expected diagnostic, the real handlers build, and bypassing the guard in Diarize alone turns the identity test red on that RPC while VAD stays green. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serve the AudioTranscription RPC Adds result_map, the engine-to-proto boundary, and wires the offline transcription RPC. The handler branches on the ROUTED task: for Asr the request's prompt is whisper-style decoding context and becomes a request option, for Alignment the same field IS the transcript to align and becomes the text input. Routing has already decided which. The result text is TaskResult.text_output verbatim and is never derived from the segments. audio.cpp carries transcript text in text_output and nowhere else, so deriving it returns an empty transcript for every producer that reports segments without word timing. transcript_assembly already enforces that; this commit's job is not to undo it at the proto boundary, and result_map_ctest pins it there. read_audio_file now takes the sample rate the caller needs. Both file-fed speech handlers ask for 16 kHz mono, for two reasons: silero_vad and sortformer_diar refuse anything else outright, which turned an ordinary 44.1 kHz upload into INTERNAL, and nemotron_asr emits word timestamps in its own 16 kHz feature domain whatever the input was, so only a 16 kHz buffer makes the emitted nanoseconds right. Zero keeps the file's native rate and channels, which is what source separation will need. LoadedModel::check_can_serve answers a capability refusal before the lane is taken and before the input file is read. Routing is a pure read of the immutable capabilities, so a model that cannot serve an RPC no longer waits out somebody else's run to say so. VAD and Diarize use it too. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): stop linking sentencepiece's vendored protobuf engine_runtime links sentencepiece, whose default SPM_PROTOBUF_PROVIDER builds the protobuf-lite 3.14.0 sources it vendors. The generated backend.pb.cc is built against the toolchain's protobuf 3.21.12. Both ended up in the binary: 476 google::protobuf:: symbols came from the archive, 278 of them also defined by libprotobuf.so, and the archive won, because once ld pulls a member in for sentencepiece's own code every reference binds to the definitions that member carries. The visible symptom is one function. ParseContext::ParseMessage(MessageLite*, const char*) is what a generated _InternalParse calls for a submessage field and for nothing else, so flat messages parsed and nested ones did not: a TranscriptResult carrying segments serialized to correct bytes that the same process could not read back, and TranscriptLiveRequest, a oneof of submessages, could not have been parsed at all. Underneath that, 3.21 generated code was running 3.14 arena, ArenaStringPtr and ExtensionSet code. -Wl,--exclude-libs does not fix it. It makes those symbols LOCAL in .dynsym and the parse still fails, because the binding was decided at static link time and no visibility flag revisits it. Setting SPM_PROTOBUF_PROVIDER to "package" before add_subdirectory points sentencepiece at the protobuf the generated code was already built against. Zero google::protobuf:: definitions remain in the executable afterwards, every nested message round trips, and citrinet_asr, which parses a SentencePiece ModelProto at load time and would break first if this were wrong, still tokenizes and transcribes correctly. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): fix the segment text a transcription response is built from Segment text is not decoration. core/http/endpoints/openai/transcription.go routes response_format text, srt, vtt and lrc through schema.TranscriptionResponse, which builds the entire body out of Segments[].Text and never reads the top-level text. So for those four formats the segment text IS the response. nemotron_asr emits one word_timestamp per SentencePiece token, and the word boundary is carried as a LEADING SPACE on the piece ("So", "me", " call"). join_words inserted a space unconditionally, so response_format=text returned "So me call me na ture ," while the correct sentence sat unread in the top-level field. The separator is now chosen from the words themselves: whole words are space-joined, subword pieces are concatenated, and one leading space anywhere selects the latter. Concatenating the real nemotron pieces reproduces text_output exactly, verified end to end. This does not touch the top-level text, which is still text_output verbatim. The rule that forbids deriving the transcript from the segments is about the direction segments -> text; segment text has no source other than its words. Two smaller corrections in the same area: timestamp_granularities ["word"] set only "word_timestamps", a key no family in the pinned upstream reads. It now sets "return_timestamps", which qwen3_asr does read and which both runs its forced aligner and shortens its chunk window, so asking for word granularity no longer silently returns nothing. The request-option comment claimed more than it delivered. prompt, translate and temperature are read by no ASR family, and are forwarded only so a family adopting them works unchanged; the comment now says so per key, and gives TranscriptRequest.diarize the same explicit treatment threads already had. Also: the shipping target now carries -Wall -Wextra -Wpedantic, which it never did, so "the build is clean" starts meaning something; and fill_transcript_result no longer swallows a null response pointer, since answering OK with an empty transcript is the one failure mode this unit exists to prevent. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serve the AudioTransform RPC Covers voice conversion, singing voice conversion, speech to speech and source separation, the four tasks LocalAI's AudioTransform can represent. AudioTransformResult carries one dst while htdemucs and mel_band_roformer produce several named stems from a single run, so inference runs ONCE, every stem is written as a sibling file <dst-stem>.<name>.<ext>, and params[stem] selects which one dst receives, defaulting to vocals and falling back to the first output. An unknown stem name is INVALID_ARGUMENT listing the real stem names rather than a silent substitution, and the selection happens before the first write so a refused request leaves no files behind. params[stem] is consumed here and is not forwarded into the engine's request options. The stem decision lives in stem_selection, which is stdlib only and therefore tested by backend/cpp/run-unit-tests.sh. It also validates the names, because they come from the model (htdemucs reads them from the GGUF's config.sources) and each becomes a component of a path this backend writes: a name carrying a path separator would escape the caller's output directory, and two stems sharing a name would silently overwrite one another. Both files are read at their native rate and channel count. Separation forces it, since demucs and roformer refuse any rate but 44.1 kHz and lose the stereo image that separates a centred vocal from a wide mix. The conversion families all resample internally (seed_vc, vevo2, miocodec, chatterbox were each checked), so passing the file through unchanged is also strictly better than band limiting it to 16 kHz first. Verified end to end against htdemucs f16 on a 44.1 kHz stereo mix: four stems plus dst, dst byte identical to the selected stem, params[stem] selecting a different one, an unknown stem refused with no files written, and mono input preserved as mono output. Also against miocodec for the single output path, where params[stem] is refused rather than ignored. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): refuse an impossible stem early, and stop blaming the caller for a failed write Four fixes from the first review of the AudioTransform RPC. check_can_serve now returns the resolved route, so params[stem] on a route that is not source separation is refused from the route instead of after a full inference: 11 ms rather than the 4.5 s a miocodec conversion costs, and far worse on seed_vc or vevo2. The post-run refusal stays as the backstop for a separation-routed family that returns no stems anyway. The typo'd-stem-name case still needs the run, since no framework header publishes the stem names before one. Stem names carrying control bytes are refused. GGUF strings are length prefixed and demucs reads its sources from JSON, so an embedded NUL survives to here: two names differing only after the NUL are distinct std::strings, so the duplicate check passes them, and then path::c_str() truncates both and they open the same file. That is exactly the silent overwrite the duplicate check exists to prevent, with the .wav lost as well. A failed write is now INTERNAL rather than INVALID_ARGUMENT. The destination is LocalAI's own generated-content directory, not anything the caller named, so a full disk or a permission fault there is a server fault and is worth retrying, which is the opposite of what INVALID_ARGUMENT tells a client. An empty output path stays INVALID_ARGUMENT. Two comment corrections and one clarification: the separators' required rate is their checkpoint's declared samplerate rather than a hardcoded 44100, seed_vc resamples with soxr and falls back to sinc-hann, and the "no files left behind" guarantee covers a refused request, not a write that fails partway through the loop. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(audio-transform): stop folding every upload to 16 kHz mono, and name the separation stems Two defects that made source separation unusable through LocalAI's own API, even though the backend served it correctly over gRPC. /audio/transform normalized every upload to 16 kHz mono s16 through utils.AudioToWav, with no way past it. htdemucs and mel_band_roformer refuse any rate but their checkpoint's own and separate a centred vocal from a wide mix using the stereo image, so every separation request through the HTTP API died with "HTDemucs prepare() sample rate mismatch: expected 44100, got 16000" while the same call over gRPC worked. The fold is not wrong, it is backend-specific: LocalVQE's echo cancellation genuinely wants 16 kHz mono and needs the reference in the same shape. So it becomes a declaration, BackendCapability.AudioTransformInputMono16k, set for localvqe and for nothing else. A backend that declares nothing gets its upload unchanged, which means no backend has to opt in to work. utils.AudioToWavPreservingShape is the non-folding conversion: a 16-bit PCM WAV passes through byte for byte at any rate and channel count, anything else is transcoded to WAV with its rate and channel layout kept. The other defect is that the run-once stem design bought nothing. A separation backend writes every stem beside dst from one inference, but AudioTransformResult carried only dst, so the other three were files no caller could find and a caller wanting all four had to run four separations. AudioTransformResult grows a repeated AudioTransformStem, the backend fills it, core/backend validates that each path really is inside the generated-content directory it handed over, and the endpoint publishes them as an X-Audio-Stems JSON header beside the existing X-Audio-Input-Url. JSON because a stem name is the model's own string and could contain any separator a hand-rolled format would use. Verified end to end through the HTTP endpoint with htdemucs f16 on a 44.1 kHz stereo file: 200 with a 44.1 kHz stereo body, all four stems named and fetchable through /generated-audio/, body byte identical to the selected stem, and params[stem]=drums returning a different one. The same upload sent to a model whose backend is localvqe still reaches the backend as 16 kHz mono, confirmed both by the engine's own rate refusal and by the persisted input file. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(audio-transform): reject extensible WAV from the passthrough, escape stem URLs, convert stems with dst Four fixes from the second review, plus one bug they made visible. isPCM16Wav tested only the bit depth, and go-audio's IsValidFile never looks at the format tag, so a 16-bit WAVE_FORMAT_EXTENSIBLE (0xFFFE) upload was passed through untouched where the old fold would have transcoded it. audio.cpp's WAV reader accepts 16-bit only when the tag is 1, so such a file died with "unsupported WAV encoding". Extensible is what many DAWs and Windows tools write and music files are this endpoint's new headline input, so it is a first-contact failure rather than a corner. The check now requires tag 1, with a spec that fails against the old implementation. Stem URLs are percent-escaped. A stem name is the model's own string and legally contains a space, a '#', a '?' or a '%'; an unescaped '#' truncates the URL before the request is even sent. The name field keeps the raw name. sample_rate and response_format are applied to the stems as well as to dst. Applying beat documenting: dst IS one of those stems, so leaving them alone broke the "dst duplicates the selected stem" invariant the whole design rests on, and both conversions are no-ops when unset. A stem whose conversion fails is dropped from the header rather than advertised in the wrong shape. Verifying that turned up why it had never been noticed: the two fields were never bound at all. The request arrives as multipart/form-data and echo's binder falls back to the FIELD NAME without a form tag, matching only case-insensitively, so "SampleRate" never matched "sample_rate" and "Format" never matched "response_format". Both were documented in the endpoint table and silently ignored. Two form tags fix it, and with them the conversion is observable end to end. Docs: audio-transform.md now documents what LocalAI does to an upload before the backend sees it, which backend gets the 16 kHz mono fold and why, params[stem], and the X-Audio-Stems header with a worked example. Also records the known limitation that the fold lookup is on the bare backend name, so pinned variants (vulkan-localvqe) do not match, and points at IsLlamaCppBackend as the suffix-tolerant precedent. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serve the TTS and SoundGeneration RPCs TTSRequest.voice is treated as a speaker reference clip when it names an existing regular file, which makes routing prefer VoiceCloning, and as a named preset otherwise, in which case it travels as VoiceReference::cached_voice_id. Both the clip and SoundGenerationRequest.src are read at the file's own rate and channel count: upstream's own CLI and server do exactly that, every consuming family resamples internally and mostly with a better resampler than ours, and ace_step and stable_audio resample their input per channel, so a downmix here would delete the stereo image they are built to consume. The request builders live in their own unit rather than in grpc-server.cpp's anonymous namespace so they can be tested; grpc-server.cpp has a main() and cannot be linked into a test binary. The option keys are the whole point of these functions, so each one was grepped against the pinned upstream and the accounting is written down beside it. instructions maps to "instruct", which is what upstream's own server maps the OpenAI field to and what qwen3_tts and omnivoice read, and to "caption" for irodori_tts; the style tag is spelled "instruct" too, because "instructions" is looked up nowhere. duration maps to "duration_seconds", read by all three generation families, with the proto's own name kept only as a forward-tolerant alias. Keys that no family reads say so. Both handlers answer a capability refusal before taking the lane and before any file read, so a model that cannot synthesise does not queue behind somebody else's run to be told no. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): stop emitting an empty style language, and name the missing clip StyleCondition::language was set whenever has_language() was true, with no !empty() guard, while the language option twelve lines below had one. core/backend/tts.go sets Language unconditionally, so has_language() is true on every request LocalAI sends and carries "" when the caller named none. An engaged-but-empty style language is worse than an absent one: supertonic reads text_input->language behind its own !empty() guard and then overrides it from style->language with no guard at all, so "" replaced its "en" default and its tokenizer threw "invalid Supertonic language: ". Every /v1/audio/speech request that set instructions and no language would have been an INTERNAL against a supertonic model. A plain request never saw it, because the style condition only exists when instructions are non-empty, which is why the chatterbox end to end run did not catch it. TTS also stops discarding the Route that check_can_serve already returns. A family routed to voice cloning without a reference clip used to be refused from inside its own prepare(), which meant an INTERNAL naming neither the RPC nor the field to set; chatterbox advertises clon and no tts, so that was every preset-only request to it. It is now an INVALID_ARGUMENT naming TTSRequest.voice, answered in about 4 ms, and it cannot misfire because has_voice_reference is what selected cloning in the first place. Reading CapabilitySet::supports_speaker_reference to generalise this stays a follow-up. The src read carries a written caveat rather than a family blocklist, because ace_step's editing routes legitimately need src: setting src on a stable_audio model corrupts the heap and aborts the process in the pinned upstream, and the only thing keeping that off the network is that schema.ElevenLabsSoundGenerationRequest has no field for it. Nobody reading that Go schema would know why, so the reason is recorded where the field is read. build_tts_shape is extracted so TTSStream cannot describe the same request differently, and it arrived untested: two mutations of it survived until a test_tts_shape case was added. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serve the TTSStream and AudioTranscriptionStream RPCs TTSStream leads with a streaming WAV header carrying 0xFFFFFFFF sizes, matching the convention backend/go/vibevoice-cpp established, so an HTTP client can start playback before the full PCM exists. Its chunks are read from StreamEvent::named_audio_outputs and not audio_output: supertonic, omnivoice and voxcpm2 all put their streamed audio there and leave audio_output empty until the very end, so reading the obvious field yields a stream with no audio in it. The finish_stream result is the family's own merged whole rather than a tail, so it is emitted only when nothing was streamed. Streaming transcription sends incremental deltas and degrades to a single delta plus the final result on families that offer no streaming ASR, which is the same message sequence with fewer deltas. The four streaming ASR families disagree on what partial_text means: nemotron_asr, vibevoice_asr and higgs_audio_stt report incremental fragments while voxtral_realtime reports the whole hypothesis and reports it twice, so the reconciliation lives in one tested unit rather than in the handler. nemotron_asr reports only through the stream event sink, and only from inside finalize, so the audio driver installs one and clears it again before returning: the session is cached and a sink left holding the caller's frame is a use after free waiting for the next stream. begin_stream is now the only implementation of the streaming state obligation, prepare then start_stream. Streaming sessions are cached, and what clears the previous stream is start_stream's reset; a family override that dropped it would break every call site with no compile error, so there is one call site. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): keep streaming deltas on UTF-8 boundaries, refuse dtypes that abort TranscriptStreamResponse.delta is a proto3 string, whose wire format requires valid UTF-8. voxtral_realtime reports its hypothesis as a concatenation of raw token BYTES (tokenizer_text.cpp:171-183), so the cumulative difference between two consecutive reports is eventually a lone continuation byte, and the C++ runtime serializes that with only a logged warning while the Go runtime refuses to unmarshal it: the client loses the remaining deltas AND the final_result. Measured on a trace of a non-ASCII sentence, 11 of 31 messages failed to unmarshal and every accented character was lost. TranscriptDeltaTracker now holds back an incomplete trailing sequence and merges it into the next fragment; reconcile flushes it, which it always can because the final text is complete. The same trace now unmarshals in full with zero failures. A streaming buffer whose float count is not a whole number of frames is refused rather than truncated. The integer division dropped the tail floats from the fed audio and therefore from the transcript, with no diagnostic; vibevoice_asr refuses the same thing from the other side of the call. A supertonic GGUF whose weights are not f32 is refused at load. It reaches ggml_concat with mismatched operand types and ggml_abort takes the whole backend process down on the first request, so nothing downstream can report it: the model loads, then every request kills the process. Attributed rather than assumed, the unary TTS path aborts identically, and upstream records that package as untested. The refusal names the orig package and says what to run before deleting the guard. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): stop a repeated lead byte from orphaning the next delta The first UTF-8 fix closed the cumulative half only. Rule 2 discards a fragment the known text already starts with, and when that fragment is the LEAD BYTE of a new character it looks exactly like a repeat of an older character beginning with the same byte. It was discarded rather than held, its continuation bytes then arrived alone and began the next delta, and utf8_complete_prefix_length only ever inspected the trailing sequence, so a delta invalid at the FRONT went out whole. Through a real Go proto.Unmarshal the review's four-character repro gave 3 deltas, 2 unmarshal failures and a lost transcript. Reachable from the incremental families, not only from voxtral: nemotron_asr's decoder cuts at a byte offset and vibevoice_asr's common_prefix_size compares bytes, so both split characters. Measured over 30,000 randomized incremental traces, 53.28% of Japanese traces and 9.52% of French ones carried at least one delta the Go runtime refuses. Two changes. Rule 2 no longer judges a fragment that ends mid-character, so the lead byte is held instead of swallowed and the character survives intact; the cost is a few duplicated bytes in a shrinking cumulative report, which no pinned family produces. release() additionally drops leading orphan continuation bytes, so no delta can begin mid-character whatever the rules above it decide. Losing a byte keeps the stream alive; emitting one ends the RPC and takes the final_result with it. Post-fix all 60,000 traces produce zero unmarshal failures, and the cumulative streams plus both pure-ASCII incremental streams are byte-identical to the previous commit, so nothing changed for the families already working. The weight-dtype allow list moves to family_gate, where it is stdlib-only and pinned by a test rather than only by a comment. Two comment citations corrected. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): read only an exact repeat as a repeat, not any prefix Rule 2 discarded any partial the known text merely started with. For a cumulative family that is a duplicate; for an incremental family it is an ordinary short fragment that happens to coincide with the start of the transcript, and it was dropped, silently corrupting the text. Pure ASCII, no multi-byte character anywhere: the fragments "pure ", "ascii ", "trans", "c", "ri", "p", "t" left the client holding "pure ascii transcrit". Over 5,000 randomized traces per transcript, 9.50% of pure-ASCII and 29.12% of French traces ended with the client holding something other than final_result.text, with a 200 and no diagnostic. Both incremental families emit fragments that small routinely, since nemotron_asr cuts at a byte offset and vibevoice_asr at a common prefix. Narrowing rule 2 to an exact repeat drives that to zero on all six transcripts and changes no cumulative stream at all: 30,000 randomized cumulative traces are byte-identical to the previous commit. What rule 2 guarded was established from upstream rather than from its own comment. The only duplicate any pinned family produces is voxtral_realtime's, where process_available_stream_chunks feeds each event to the sink from inside its loop and returns the last of the batch, so that event arrives twice with byte-equal text. A duplicate is an exact repeat, so equality still covers it. The case given up is a cumulative report that SHRINKS, which no pinned family can produce: voxtral decodes a token vector that is only push_back'ed and cleared by reset(), so within a stream it can only grow. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): serve the AudioTranscriptionLive RPC The one bidirectional stream this backend serves. The client sends a TranscriptLiveConfig, then TranscriptLiveAudio frames; the server acknowledges with ready, emits deltas as the audio arrives, and sends final_result once the read side closes. There is no offline fallback: live transcription has to consume audio incrementally, so a family with no streaming ASR is refused rather than served a batch run, which is what this RPC's Streaming-only mode_candidates list already says. The driver is a new sibling of run_streaming_audio, run_streaming_live, because the audio does not exist yet: instead of slicing a buffer it pulls frames from the caller until the read side closes. It installs the same ScopedStreamSink in the same order, which is not optional, since nemotron_asr returns a bare event from process_audio_chunk and reports every partial through the sink from inside finalize(). It buffers the wire's frames up to the family's own preferred window rather than feeding whatever size the client's audio callback produced, and it does not call finish_stream at all when no audio arrived, because nemotron_asr throws "finalize requires streamed audio" and an empty transcript is the truthful answer to transcribing nothing. Three things the handler had to get right and one it cannot: - The audio contract. A live request carries no samples, but nemotron_asr's streaming prepare() throws without an audio contract, and build_preparation_request derives it from TaskRequest::audio_input, so that field is an EMPTY buffer holding only the rate and the channel count. - 16 kHz or a refusal. The families express their spans in their own 16 kHz feature domain whatever the input was, and live frames cannot be resampled on the way in the way a file can, so an 8 kHz session would return timestamps 2x off with a 200. core/backend hardcodes 16000 anyway. - A mid-stream Config is refused. backend.proto calls it a decoder reset, but deltas already on the wire cannot be retracted, so a reset would leave the final text contradicting the transcript the client assembled. Ignoring the message would hand a client that believes it reset the decoder a transcript that silently continues the audio it thought it discarded. - The stale-route identity check cannot run here: TranscriptLiveRequest carries no ModelIdentity in either arm of its oneof, so snapshot_for does not instantiate for it. snapshot_unchecked's comment now names that as a second legitimate class of caller and says the fix is a proto change. eou and eob stay false. They exist for cache-aware models that emit end-of-utterance and end-of-backchannel tokens; audio.cpp's StreamEvent has no equivalent signal, and a client uses eou to decide the speaker yielded the turn, so a guess inferred from silence cuts people off mid-sentence. The lane is held for the whole stream, which is as long as the user keeps talking: the streaming session is stateful and cached, so a concurrent run would interleave two callers' audio and corrupt both transcripts. Verified against nemotron_asr over a real connection with a 14 s WAV in 512-sample frames: ready first, 59 incremental deltas with no repeated prefix, concat(deltas) equal to final_result.text, word timestamps in nanoseconds, eou and eob false. citrinet_asr answers UNIMPLEMENTED naming the family and listing asr/offline. A config followed by a close returns an empty final_result rather than hanging, and a first message that is not a config is INVALID_ARGUMENT. Two concurrent streams both return the complete transcript. Two cleanups on lines Task 12 touched, folded in. The DtypeAllowList terminator is now asserted at compile time: the reported out-of-bounds read did not exist, the single entry does terminate, but the loops have no other bound and any edit that widened an entry would walk off the end. And the dtype guard now short-circuits on "is there a table entry" through a new predicate rather than on the emptiness of the description string, which would have skipped the check on an entry with an empty allow list, i.e. on precisely the entry that refuses every dtype. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): bound the lane a live stream can hold AudioTranscriptionLive holds the model's inference lane for the whole stream, which is correct (the streaming session is stateful and a concurrent run would interleave two callers' audio) and newly dangerous. Every other RPC holds the lane across compute, or across a write to a slow reader, and both of those terminate on their own. A live stream instead blocks in a client-driven read, and a peer that goes silent WITHOUT closing the stream never terminates anything: the lane stays taken and every other request against that model queues behind a client that stopped speaking. live_watchdog is a one-shot idle timer that ends the stream when no frame has arrived inside a window. It is standard library only, so it is unit tested without an engine. gRPC's synchronous Read has no timeout and cannot be given one, so the only way to unblock it is ServerContext::TryCancel, which decides the wire status itself: the client sees CANCELLED rather than the DEADLINE_EXCEEDED the handler returns, the reason is logged, and the lane coming back is the point. When it fires the read loop throws rather than reporting end-of-input, so the driver does not go on to finalize a decode nobody is waiting for. It is armed only after the lane is taken and disarmed as soon as the read side closes, and both ends matter. Arming earlier would cover acquire(), which legitimately blocks while another live stream runs, so a queued caller would be cancelled for waiting its turn. Disarming later would cover our own decode, where a window overrun is not a peer going quiet and cancelling would throw away the transcript the client is waiting for. The window is the new live_idle_timeout_ms option, 30 s by default, 0 meaning no limit. core/http/endpoints/openai/realtime.go drives a 300 ms ticker and feeds every tick that produced new audio while a turn is open, so 30 s of silence is a hundred ticks that delivered nothing. It is also longer than any pause a speaker takes mid-utterance, which is the case that must never be cut off, and backend.proto lets one stream span many utterances, so a client that pauses longer between them raises the option rather than discovering it. Two smaller corrections in the same handler: - check_can_serve now runs BEFORE the sample rate check. pkg/grpc/grpcerrors/errors.go degrades to the file path on UNIMPLEMENTED and on nothing else, so a live-incapable model asked at a wrong rate was answering INVALID_ARGUMENT and costing the caller its fallback. - a negative sample rate is refused instead of silently becoming 16000. Zero still means 16000, which is what the proto documents; -1 is malformed rather than absent and gets the same refusal every other bad rate gets. And one thing recorded rather than changed, at the handler: "live" here means incremental INPUT, not low latency, and with the pinned families it does not yet mean incremental OUTPUT either. nemotron_asr's process_audio_chunk only appends to its buffer, so its whole decode and every delta happen inside finalize(), after the client closes its send side. The policy-window buffering is inert for that family and matters only for vibevoice_asr and higgs_audio_stt. Verified on the wire with live_idle_timeout_ms:3000. A silent client acked at 371 ms and was cancelled at 3.371 s; a second live stream opened one second later received its ack 2.37 s in, i.e. at the instant the first was cancelled, and then transcribed successfully on the same cached session. Without the watchdog it would still be waiting. Re-ran the live transcription (ready first, 59 incremental deltas, concat equal to the final text, word timestamps in nanoseconds, eou and eob false), the citrinet refusal at both a right and a wrong rate (UNIMPLEMENTED either way now), and Task 12's AudioTranscriptionStream on nemotron_asr, which is unchanged. Mutation testing the watchdog found a weakness in its own test: the destructor test slept past the window inside the watched scope, so a destructor that DETACHED the thread instead of joining it passed unnoticed. The test now uses a window longer than the scope, which kills that mutant, and says why. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): refuse the unsupported RPCs with a reason AudioEncode, AudioDecode, AudioTransformStream, AudioToAudioStream and VoiceEmbed have no counterpart in audio.cpp's VoiceTaskKind. Each now returns UNIMPLEMENTED naming the loaded family, what that family does support, and the upstream limitation, instead of the generated base class's bare status. The reasons live in a table in capability_routing.cpp so they are data rather than literals copied into five handlers, and so a test can assert every one of them. The five claims this was planned against were re-read at the pinned upstream e800d435d130dc776baf6f3e6129bb62b1495c89, and one did not hold. "audio.cpp streams tts and asr only" is false: silero_vad advertises vad with RunMode::Streaming. The refusal stands on the narrower claim that survives, that no family advertises streaming for any task AudioTransform routes to, and a test asserts the refuted wording does not come back. VoiceEmbed is the one refusal whose request carries a ModelIdentity, so it runs the #10952 check before answering: a stale route must get NOT_FOUND and the router's sentinel, not "audio.cpp cannot embed speakers" about a model that is not loaded here. It cannot use snapshot_for, whose no-model branch would tell the caller to load a model when no model can help, so it takes the reference through snapshot_unchecked and checks identity itself. That function's comment now names three classes of caller instead of two. The two bidirectional surfaces refuse without reading their stream, verified with a client that writes a config and eight frames first and gets the status rather than hanging. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): correct the vevo2 clause, and assert the absences Review found a false clause in the AudioToAudioStream refusal. It said s2s is "offline voice conversion ... which converts one clip into another speaker's voice", which is true of miocodec and false of vevo2: vevo2's s2s route is `editing` and only `editing` (default_route_for_task and route_matches_task in src/models/vevo2/session.cpp), documented as "Edit source speech into new target text while using the target voice" and requiring --target-text, so it rewrites what was said. vevo2's voice conversion is its separate vc task. It now reads "offline clip-to-clip processing against a target voice, declared only by miocodec (voice conversion) and vevo2 (speech editing)", and a test asserts the miscast cannot come back. The conclusion is unchanged: neither family converses. That defect was undetectable on the wire, since vevo2 does not load here, which is the argument for upstream_absence_ctest.cpp. It links engine_runtime purely to interrogate make_default_registry() and asserts the five premises the refusal reasons rest on: no codec task kind, no family advertising spk, no streaming for sep/vc/svc/s2s, miocodec advertising exactly vc and s2s, and s2s advertised by exactly miocodec and vevo2. The last two are exact sets, so an addition fails here rather than leaving a message stale. A positive control proves the registry is populated and the query works before any absence is believed, and every assertion has a reproduced negative control. This turns an AUDIO_CPP_VERSION bump from "remember to re-read five prose paragraphs" into a test failure. unsupported_surface now switches over UnsupportedRpc with no default label, so -Wswitch reports a sixth enumerator added without a row at build time; the runtime bounds guard it replaces is deleted. The AudioTransformStream reason had a true premise and an overreaching conclusion: an offline sep family could be buffered into a stream, as other LocalAI backends do. It now says this backend declines to offer a buffered offline call in disguise, rather than implying impossibility. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): make the missing-switch-case diagnostic fatal unsupported_surface() switches UnsupportedRpc onto the table row that explains it, with no default label, so -Wswitch reports an enumerator nobody handled. As a warning that is not enough: adding a sixth enumerator and building the shipping target gives exit 0, a binary and one warning, and the trailing `return surfaces[0];` then answers the new RPC with AudioEncode's codec reason. That is a confident, specific and false statement about audio.cpp on the wire, on the one code path whose entire job is to be truthful about what this backend cannot do, and it is worse than the runtime fallback it replaced, which at least named itself as a bug in this file. capability_routing.cpp therefore joins loaded_model.cpp on the existing -Werror=switch pin, whose comment already made this argument for the engine enum. The comment now covers both files. The pin stays per-file rather than project-wide because upstream's own ace_step/vae_decoder.cpp has unhandled -Wswitch cases of its own. Verified: a sixth enumerator now fails `make grpc-server` with exit 2 and no binary; appending a 14th VoiceTaskKind upstream still fails loaded_model.cpp, so the two pins fire independently; both reverted clean. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): package the backend image Bundles the dependency closure for the from-scratch image, the dlopened ggml CPU-variant shared objects that ldd cannot see, and upstream's bundled silero_vad and marblenet_vad assets so VAD works with no download. The bundled loader sits in the package ROOT rather than at lib/ld.so. run.sh execs it, which makes /proc/self/exe name the loader, and this backend has two consumers of that path: ggml discovers the libggml-cpu-*.so by listing dirname(/proc/self/exe), and resolve_model_path expands bundled:<name> under the same directory. Rooting the loader makes the binary, the ggml objects and assets/ share the one directory all three resolution mechanisms agree on. llama-cpp's lib/ld.so layout would need assets/ moved into lib/ as well. The image builds against apt gRPC and protobuf, like Dockerfile.ds4 and unlike Dockerfile.privacy-filter. The from-source gRPC that install-base-deps.sh and the base-grpc-* images supply vendors protobuf 26, which pulls abseil into message_lite.h; with SPM_PROTOBUF_PROVIDER=package that collides with sentencepiece's vendored mini-abseil and every absl::internal reference becomes ambiguous. Noble's protobuf 3.21.12 predates the abseil dependency and is the pair every earlier verification of this backend ran against. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): exempt the driver libraries from the packaging gate package.sh already left libcuda.so* and libnvidia-* to the host when copying, because the driver has to match the kernel module on whatever host runs the image, but the validation gate had no matching exemption. With BUILD_TYPE=cublas ggml is static and links CUDA::cuda_driver, so grpc-server carries DT_NEEDED libcuda.so.1 and the gate would have rejected the very absence the copy loop created, failing every cublas build in CI. One regex now feeds both. Building a control for that found a second defect: ld.so --list refuses to trace an object with an unresolvable dependency at all, exiting 127 without emitting a per-library line, so the "=> not found" rule was dead code and no exemption could have applied to it. The gate now traces with LD_TRACE_LOADED_OBJECTS and LD_LIBRARY_PATH, which reports the missing name and exits 0, and which is also what run.sh does at run time. Adds a layout assertion so a future move of the loader into lib/ fails the build instead of shipping a package that resolves bundled: models into lib/assets and finds no ggml CPU backend, and records for Task 16 that the Darwin script must not be a straight copy of privacy-filter-darwin.sh, which never calls package.sh and would silently drop assets/. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): register the backend with CI and the gallery Adds the five Linux matrix entries (cpu amd64/arm64 sharing a tag-suffix so the manifest merge fires, cuda 12, cuda 13, vulkan), the path-filter case that keeps later PRs touching backend/cpp/audio-cpp/ from getting zero CI jobs, the bump-bot entry pointing at the AUDIO_CPP_VERSION pin in the backend Makefile, the gallery meta plus its -development variant and the image entries for every variant, and the Makefile docker-build wiring. The matrix entries carry base-image only, with no builder-base-image, unlike the llama-cpp and privacy-filter blocks they sit next to. The prebuilt quay.io/go-skynet/ci-cache:base-grpc-* images ship a from-source gRPC whose protobuf v26 depends on abseil, and this backend's sentencepiece is built with SPM_PROTOBUF_PROVIDER=package, so it sees real abseil's absl::lts_20240116:: internal alongside its own vendored plain absl::internal and every absl::internal:: reference becomes ambiguous. Building against base-grpc-amd64 fails at sentencepiece-static.dir/error.cc.o with "reference to 'internal' is ambiguous". Dockerfile.audio-cpp installs apt's gRPC/protobuf 3.21.12 itself, which is also the pair every unit and end-to-end run of this backend has been verified against, and the CUDA toolkit therefore has to come from base-image. No Darwin matrix entry and no metal gallery entries: the Metal build needs scripts/build/audio-cpp-darwin.sh, a backends/audio-cpp-darwin make target and a routing step in backend_build_darwin.yml, none of which exist yet, so an entry added now would be routed to build-darwin-go-backend and look for backend/go/audio-cpp/. The inferBackendPathDarwin case and the DARWIN_BESPOKE_BUILDERS membership are in place, inert, so that adding the entry later is a one-line change that cannot be claimed by the generic Go path. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): pin the CUDA architectures, drop the vulkan variant Upstream sets CUDA_ARCHITECTURES to `native` on the engine_runtime target whenever CMAKE_CUDA_ARCHITECTURES is unset at root scope, and docs/build/ linux.md says so outright. ggml's own default does not rescue it: it list(APPEND)s in the ggml subdirectory scope, which never reaches the root scope where the engine_runtime property is decided. No CI runner has a GPU for `native` to enumerate, so both cublas entries would have gone red on the very commit that first turns a CUDA build on. Pin the list in backend/cpp/audio-cpp/Makefile, selected by CUDA_MAJOR_VERSION, which Dockerfile.audio-cpp now forwards from the CI build-arg it was previously discarding. The values are copied from ggml's own version guards rather than invented, so engine_runtime and ggml compile for the same set: CUDA 12 keeps the Maxwell/Pascal/Volta virtual archs and stops at 120a-real, CUDA 13 drops them and adds 121a-real. The `a` suffix is used rather than `f` because the latter needs CMake 3.31.8 and Ubuntu Noble ships 3.28.3. Verified by driving CMake 3.28.3's own CUDA architecture validator over both lists, with 120f-virtual as the rejected control. Drop the vulkan matrix entry, its two gallery entries, the vulkan capability key on both metas and the Vulkan tag. Every other vulkan backend gets its Mesa ICD drivers from .docker/install-base-deps.sh, which package-gpu-libs.sh then bundles; Dockerfile.audio-cpp calls neither and installs only libvulkan-dev and glslc, so the image would ship a Vulkan loader that finds no GPU. No CI job runs a vulkan image against real hardware, so that would have passed green and failed in users' hands. BUILD_TYPE=vulkan stays supported for local builds. Also note on the cublas entries that cuda-major-version now selects the architecture list and that cuda-minor-version and the base-image tag encode the same toolkit, and correct the stale entry counts on matrixEntryKey. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): build for Darwin Metal Bespoke C++ Darwin path like ds4 and privacy-filter: an includeDarwin matrix entry, a backends/audio-cpp-darwin make target, a gated workflow step, and the metal image entries plus metal/metal-darwin-arm64 capability keys in the backend gallery. The build script deliberately does NOT reassemble the package the way privacy-filter-darwin.sh does. It runs the backend's own `make package` and copies the result, so the Darwin package keeps the root-level layout the Linux one has: grpc-server, run.sh, the ggml objects and assets/ in one directory, with lib/ for the dylib closure. Hand-assembling would drop assets/, and assets/ is what makes the bundled: model paths resolve with nothing downloaded. The dylib walk is a full transitive closure rather than the single level ds4 and llama-cpp do, because Homebrew's grpc++ pulls libgrpc, abseil, upb, cares and OpenSSL that grpc-server does not link itself, and a level-1 walk ships a package that only works on a machine that already has Homebrew grpc. Two fixes folded in, both in the backend Makefile: - an EMPTY CUDA_MAJOR_VERSION fell through to the CUDA 12 architecture list, which contains 120a-real and so needs nvcc >= 12.8. A local BUILD_TYPE=cublas build on a 12.0-12.7 host failed to compile where upstream's documented default (native) worked. EMPTY now maps to native, 12 and 13 keep their lists, and any other non-empty value is an error on cublas builds. CI always passes a major, so CI is unaffected. - the Darwin branch now points CMake at Homebrew's keg-only libomp. AppleClang ships no OpenMP runtime and nothing is symlinked into /opt/homebrew, so FindOpenMP finds neither the library nor the header, and audio.cpp calls find_package(OpenMP REQUIRED) whenever ENGINE_ENABLE_OPENMP is on. Without the hint the macOS build would have died at configure time. If the keg is absent the build disables OpenMP instead of failing. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): make the Darwin fallbacks loud and the rpath walk complete Review follow-up on the Darwin Metal build. The OpenMP fallback was silent. If brew --prefix libomp ever comes back empty, CI produced a green Metal package with 108 #pragma omp directives across ~30 files compiled out, and clang says nothing about an ignored omp pragma without -Wsource-uses-openmp, so the only trace was one absent flag inside a set -x cmake line. That regression would have been blamed on Metal. It now warns. The @rpath arm of the dylib walk had no live candidate when it was written, on the reasoning that a Metal build links ggml statically. The OpenMP fix in the same commit made libomp.dylib one, and whether Homebrew records it as an absolute opt path or as @rpath/libomp.dylib is not observable from Linux. The walk now expands @rpath, @loader_path and @executable_path against the object's own LC_RPATH entries, and only fails when nothing on disk answers, printing the rpath list with the error so a failure on a machine nobody can attach to explains itself. Also: ADDITIONAL_LIBS now go through the closure rather than a bare cp, so they are deduplicated and their own dependencies bundled; build/darwin/lib is created explicitly instead of relying on package.sh pre-creating it; the libomp probe uses nested ifneq rather than $(and ...), which needs GNU make 3.81 and would otherwise expand empty and take the OFF branch on an older make; and -DOpenMP_ROOT is quoted like its CUDA sibling. Verified with a Linux harness that runs the script verbatim against a stubbed otool: a level-2 transitive dep, an @rpath dep reachable only through LC_RPATH, and an ADDITIONAL_LIBS dep are all bundled, a dependency cycle terminates, system libraries are skipped, the packaged tree has assets/ at the root beside grpc-server with the dylibs in lib/, and both failure paths exit non-zero. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): make bundled: reachable from a model YAML resolve_model_path() tested the bundled: prefix on `candidate`, which prefers ModelFile and falls back to Model. LocalAI fills ModelFile by joining ModelPath onto the configured model string (pkg/model/loader.go, LoadModelWithFile), and only sets it from a managed artifact otherwise, so a model YAML saying `model: bundled:silero_vad` arrives as ModelFile "/models/bundled:silero_vad" and Model "bundled:silero_vad". The prefix therefore never matched through the normal load path: it matched only for a hand-written LoadModel call that left ModelFile empty, which is exactly how task 15 verified it, and every model YAML using the form failed with "model path does not exist: /models/bundled:silero_vad". Both fields are now checked, Model first, so the zero-download VAD path the package ships assets for is reachable the way it is documented. A caller that puts the form in ModelFile still works, so task 15's verification stands. Compiled clean; the runtime check could not run on this host, whose system libprotobuf/libre2 have gone missing (the pre-existing grpc-server binary no longer resolves its libraries either), so it wants a container run. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): advertise the backend and document its options Registers audio-cpp as preference-only in /backends/known: the family lives in GGUF metadata that an importer cannot read from a remote repo, and one repo hosts thirty families, so there is no honest auto-detect signal. Modality is a single string and the import form chips on a fixed key set, so it registers as tts with the other modalities named in the description rather than under an invented key the UI would bucket as "other". Adds a features page covering the option namespacing, the routing table per endpoint, the RPCs this backend declines and why, the bundled VAD path, the separation stem behaviour, and the family gotchas (supertonic needs the orig package; chatterbox advertises cloning and no plain tts; nemotron_asr defers its whole decode to finalize so live transcription emits nothing until the client half-closes, unlike higgs_audio_stt and voxtral_realtime). Every option name and family capability in it was read off the pinned upstream checkout. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * backend(audio-cpp): test resolve_model_path, and correct the family names The bundled: fix in |
||
|
|
7d8e0bac18 |
fix(model): deterministic, type-filtered backend auto-detection (#9287) (#10286)
* fix(model): deterministic, file-type-filtered backend auto-detect (#9287) When a model config declares no explicit `backend:`, Load() fell into a trial loop built by ranging the external-backends Go map (random order) with no filtering, returning the first backend whose gRPC LoadModel succeeded. An unrelated installed backend - e.g. the "opus" audio codec - could therefore win a GGUF/LLM model load, so a model that should run on llama.cpp wrongly tried to use opus. Extract the candidate selection into a pure, testable function SelectAutoLoadBackends that: - sorts the candidate list deterministically (no more map-order nondeterminism), and - for a `.gguf` model, filters to LLM-capable backends (via core/config.BackendCapabilities) and puts llama-cpp first, so an incompatible audio/codec/image backend can never win the trial loop. If filtering would leave zero candidates, the full sorted set is returned unchanged, so a previously-loadable model is never made unloadable. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(model): break core/config <-> pkg/model import cycle in backend auto-detect The #9287 auto-detect change made pkg/model/autoload.go import core/config for the backend capability table. core/config already imports pkg/model (runtime_settings_registry.go uses model.DefaultWatchdogInterval), so this closed a core/config -> pkg/model -> core/config import cycle and broke the build and golangci-lint. Invert the dependency so the lower-level pkg/model no longer imports the higher-level core/config. pkg/model exposes RegisterLLMCapableBackendFunc and uses the registered predicate; core/config (which owns the capability table) registers it from an init(). The deterministic, GGUF-type-filtered selection behaviour is unchanged. When the predicate is unwired the GGUF filter is skipped, preserving the existing zero-candidate fallback. The unit test now injects a fake capability predicate so SelectAutoLoadBackends is exercised independently of the core/config table. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:opus-4.8 [Claude Code] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: localai-org-maint-bot <bot-opensource@localaisrl.com> |
||
|
Richard Palethorpeandlocalai-org-maint-bot
|
9058a2bb46 |
feat: Add 3d generation UI/API and trellis2cpp backend (#10979)
* feat(3d): add Generate3D RPC, FLAG_3D capability, and /v1/3d/generations endpoint Adds the plumbing for image-conditioned 3D asset generation (binary glTF / GLB output), modeled on the video generation path: - backend.proto: Generate3D RPC + Generate3DRequest (staged image src, glb dst, seed/step/cfg_scale/texture_steps, quality and background enums, params map for backend-specific extras) - pkg/grpc: thread Generate3D through client, server, embed, base and the backend interfaces; connection-evicting and distributed-node wrappers (in-flight tracking + file staging) included - core/config: FLAG_3D usecase (guessed only for the trellis2cpp backend), '3d' canonical usecase string mapped to the Generate3D method, and a '3d' output modality - REST: POST /v1/3d/generations (+ unversioned alias) returning OpenAIResponse with a /generated-3d URL or b64_json; conditioning image accepted as URL, base64, or data URI; quality/background validated at the edge; .glb served as model/gltf-binary - auth: '3d' route feature (default ON); /api/instructions entry Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(trellis2cpp): add the trellis2.cpp image-to-3D backend Wraps localai-org/trellis2cpp (C++/GGML port of Microsoft TRELLIS.2, pbr-textures branch) as a Go+purego backend, following the stablediffusion-ggml pattern: - backend/go/trellis2cpp: purego bindings to the flat C ABI (v9, asserted at startup), eager pipeline load with model-set validation (refuses non-trellis GGUFs; degrades coarse/geometry-only/textured exactly like the upstream demo), Generate3D via t2_generate + t2_bake_glb writing a binary glTF to dst. Weight-free unit tests cover resolution/validation/param mapping — CI never downloads the multi-GB GGUF set or runs inference. - CPU SIMD variants build into per-variant directories (the shared libggml sonames collide across variants, unlike sd-ggml's flat renamed-.so scheme); run.sh picks one via /proc/cpuinfo. - CI wiring: backend-matrix entries (cpu, cuda12/13, vulkan amd64+arm64, l4t, l4t-cuda13, darwin metal), index.yaml meta + latest/master image entries, bump_deps tracking of the pbr-textures branch, changed-backends.js mapping, top-level Makefile targets. - Importer: auto-detects trellis GGUF repos/URIs (registered before llama-cpp so the .gguf match isn't stolen) and expands any trellis URI to the full 10-file component set spanning the three LocalAI-io HF repos. - Gallery: trellis2-4b (full PBR + 1024 cascade) and trellis2-4b-geometry (512 untextured) with verified sha256s. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(ui): 3D generation page with native GLB viewer and IndexedDB history Adds a Studio tab + /app/3d page for the new image-to-3D endpoint: - GlbViewer ports the trellis2cpp demo's dependency-free WebGL2 renderer (quaternion trackball, metallic-roughness PBR, ACES, hidden-line wireframe with a bounded index budget) and pairs it with a minimal GLB parser for the two forms t2_bake_glb emits — dense vertex-PBR (linear COLOR_0 + _METALLIC_ROUGHNESS, uploaded as normalized integers) and the opt-in UV-atlas textured form. Parsing happens before any GL so stats and errors render without WebGL2. - use3DHistory stores past generations (params, input thumbnail, and the GLB blob itself) in IndexedDB with keep-newest-20 eviction — GLBs are multi-MB binaries localStorage can't hold — and the page offers a download button for the active GLB. - Wiring: CAP_3D capability constant (FLAG_3D — the exact string /api/models/capabilities serves), threeDApi, router entries, Studio tab, vite dev proxy, en locale keys. - e2e: render-smoke entry plus a focused spec that feeds a real one-triangle vertex-PBR GLB through the parser/viewer and exercises IndexedDB persistence, selection, deletion, and API errors. Assisted-by: Claude:claude-fable-5 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(3d): address API correctness and UX issues Keep 3D generation on the LocalAI-specific /3d/generations route and ensure authentication and permissions cover it. Propagate distributed transfer failures, publish a portable ARM64 backend image, honor importer overrides, and align discovery, upload validation, and touch controls. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(3d): add previewable print remeshing Add a single-detail CGAL Alpha Wrap workflow for existing Trellis GLBs, including PBR reprojection, API documentation, tracing, and an in-browser preview before download. Allow the remesh route to enforce its 512 MiB upload cap independently of the smaller global default so generated high-resolution meshes can be processed. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * build(trellis2cpp): centralize remesh dependency pins Assisted-by: Codex:GPT-5 [apply_patch] [exec_command] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(kokoros): implement Generate3D stub for new proto RPC The Generate3D RPC added to backend.proto for the trellis2cpp backend made tonic's generated Backend trait require generate3_d, breaking the kokoros-grpc build. Return unimplemented like the other unsupported modalities. Assisted-by: Claude Code:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> Co-authored-by: localai-org-maint-bot <bot-opensource@localaisrl.com> |
||
|
Richard Palethorpe
|
49ef40a187 |
feat(classifier/VAD): support voice control on low power devices (#10804)
* feat(llama-cpp): route Score through the slot loop Score previously bypassed the slot loop with a direct llama_decode: a conflict guard aborted the whole process if scoring raced generation, the config validator had to reject score alongside chat/completion/embeddings, and every candidate re-decoded the full shared prompt. Add SERVER_TASK_TYPE_SCORE to the (patched) upstream server so score tasks are scheduled like any other slot work: generation and scoring serialize naturally, the shared prompt is decoded once per call, and the slot's prompt cache carries the conversation prefix across calls. Context checkpoints at the score boundary and at the cache-divergence point keep SWA/hybrid/recurrent models (e.g. LFM2.5) from re-prefilling the whole prompt per candidate: warm-turn scoring on a 6-option set drops from ~8s to ~0.5s on a desktop CPU. The conflict guard and the validation split are removed; declaring score with generation usecases on one config is now supported and shares the slot cache. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): classifier wire types and pipeline config Wire types and YAML config for realtime classifier mode: sessions carry a localai_classifier extension (options with canned replies/tool calls, softmax threshold, normalization, history trimming, fallback modes, and a deterministic wake-word address gate), mirrored by pipeline.classifier in the model YAML and surfaced in the config-meta registry. The localai.classifier.result server event reports the full score distribution per turn. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): classifier response flow Classifier-mode responses: instead of autoregressive generation, each user turn is prefill-scored against the option list (router.ScoreClassifier prompt/candidate shapes over the Score primitive) and the winning option's canned reply and tool call are emitted through the existing response machinery. Below-threshold turns take the configured fallback (none / canned reply / generate); empty transcripts and unaddressed turns (wake word not mentioned) skip scoring entirely. The scoring probe defaults to the latest user message only — small scorers echo canned replies from prior turns back as the top option otherwise. Built for hardware that can afford prompt processing but not decode: with slot-based Score the option list stays KV-cached across turns, so a turn costs roughly one forward pass over the new words. session_update_error events now carry the validation cause instead of a generic message. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): bound the VAD tick's scan window and buffer retention The VAD tick loop re-scanned the entire input buffer every 300ms and only trimmed it on zero-segment ticks or commits. Audio that keeps producing segments without a committing pause (steady noise a mic pipeline lets through, music, continuous speech) grew the buffer toward the 100MB cap with each tick rescanning all of it — O(n^2), measured at ~3.3ms of silero per buffered second: past ~90s retained, ticks run back to back and pin ~4 cores until the stream stops. Silero's recurrent state only carries a few hundred ms of context, so rescanning old audio buys nothing. Clip the slice handed to the VAD to the largest silence the commit test can need to measure (server_vad silence window or the semantic eagerness fallback) plus a warm-up margin, and rebase the returned segment times so every downstream consumer keeps whole-buffer coordinates. An open turn whose clipped window is all silence now commits (the silence outran the window) instead of being discarded as no-speech. Independently, retain at most 90s of raw buffer, rebasing the live-feed and EOU cursors on trim — this also bounds the previously unbounded VAD-error path. Turn boundaries are otherwise unchanged: no forced commits, no new coordinator states. pipeline.turn_detection.vad_window_sec can widen the scan window; values below the automatic floor are ignored. The tick body is extracted into vadTick so specs can drive turn detection synchronously (same shape as classifySoundWindow); the babble reproduction that pinned 4 cores now plateaus under 10% of one core. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(backend): let per-model threads override the global default ModelOptions overrode a set per-model threads value with the app-level --threads whenever the latter was non-zero — and WithThreads defaults it to the physical core count, so it always was. The YAML threads: knob has been dead config: a tiny VAD model could never opt down from the global pool size. SetDefaults already fills an unset per-model value from the app config, which is the intended precedence; resolve threads through a helper that honors it (explicit threads: 0 still means unset). Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(gallery): single-thread the silero VAD Silero is a ~2MB recurrent model with no exploitable graph parallelism: measured per-call latency is identical at 1 and 10 ORT threads, while every extra pool thread just spin-waits between the realtime loop's frequent tiny inferences. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * docs(realtime): classifier mode, VAD scan window, threads precedence Document the realtime classifier mode (options, threshold guidance, wake-word address gate, empty-transcript handling), the VAD scan window and 90s buffer retention (pipeline.turn_detection.vad_window_sec), the per-model threads precedence, and the M3 classifier note in the realtime state-machine design doc. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * perf(llama-cpp): score all candidates in one batched decode One scoring call is now a single SERVER_TASK_TYPE_SCORE task: the slot decodes the shared prefix (prompt + longest common candidate token prefix) once, then forks one sequence per candidate off it (metadata-only for the unified KV cache, copy-on-write for recurrent state) and decodes every candidate's unique tail in one llama_decode. Previously each candidate was its own task that restored the boundary checkpoint and re-decoded its full tail sequentially, paying per-candidate task and decode overhead. The context reserves SERVER_SCORE_FORK_SEQS extra sequence ids (and recurrent-state cells) beyond the parallel slots via the new common_params::n_seq_score_forks. Forking requires the unified KV cache (already this backend's default) since per-sequence streams would shrink n_ctx_seq; an explicit kv_unified:false disables forking and Score calls that need it fail cleanly. Candidates beyond the fork/output budget decode in successive chunks. Wire contract and scores are unchanged: per-token logprobs are stitched from the shared region and the forked tails. Verified bitwise deterministic call-to-call and independent of candidate order (no cross-fork leakage via equal-length candidate swap); ranking matches the per-candidate implementation on the drone battery (winner softmax 0.99996 vs 0.99997), and >16-candidate chunking, prefix-of-another and empty candidates all pass. Measured on a desktop CPU: warm /api/score calls 0.52s -> 0.23s; warm realtime classifier turns 196-303ms. The 9-candidate drone turn decodes ~17 unique tail tokens in one batch instead of nine sequential ~220ms checkpoint-restore tasks. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): gate scoring capacity by model usecase Reserve llama.cpp scoring slots only for models that explicitly declare the score usecase, while allowing score to coexist with chat and completion. Reject incompatible unified-KV settings and classifier activation on models without scoring capacity. Propagate application defaults when resolving realtime and preload pipeline stages so unset thread counts are resolved consistently without overriding explicit model settings. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(ci): honor APT mirrors in the prebuilt llama-cpp compile step The builder-prebuilt path installs gcc-14 with apt directly and ignored the APT_MIRROR/APT_PORTS_MIRROR build args the from-source path already honors, so an ubuntu mirror outage broke every arm64 backend build. Pass the args into the stage and run apt-mirror.sh (already in the build context via COPY . /LocalAI) before the apt step. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): classifier argument slots via constrained completion Hybrid classify-then-complete: a classifier option's canned tool call can declare typed argument slots (number | enum | string, with defaults and prompt hints) referenced as "{{name}}" in the arguments template. When the option wins, the slots are filled by a short grammar-constrained completion that continues the exact scoring prompt — rendered by the same cached ScoreClassifier, so the llama.cpp prompt cache is already warm — with the chosen route JSON re-opened at the first slot field. A GBNF grammar pins the field skeleton and frees only the values; temperature 0, a couple dozen tokens at most (~300ms on a desktop CPU for two slots). Slot declarations and hints ride the option descriptions in the shared system prompt, informing scoring and the fill alike at no per-turn token cost. The localai.classifier.result event carries the final arguments and a fill_latency_ms. On inference failure the slots' defaults apply; a slot without a default fails the response (or falls through with fallback.mode: generate). Slot filling requires completion alongside score in the scoring model's known_usecases. Verified end-to-end on the Pi drone demo: "fly forward three meters" in distance mode classifies forward and infers {"distance": 3, "units": "meters"} in ~310ms, and the drone flies exactly 3 units. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): splice filled slot values into classifier replies A classifier option's spoken reply can now reference its tool's argument slots ("Going forward {{distance}} {{units}}."): the values inferred by the slot-fill completion — or the recovery defaults — are spliced into the reply as plain text before it is emitted, so what the assistant says confirms what it actually inferred. Placeholders without a value stay literal, and options without slots are untouched. FillToolArguments now returns the raw slot values alongside the spliced arguments JSON to make the reply templating possible. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): harden classifier slot completion Reserve context for constrained slot filling, size completions from their encoded output, and encode enum grammar literals as valid JSON. Reject empty enum values and cover the failure modes with regression tests. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): prewarm the classifier scoring prompt on registration Swapping a session's classifier option list (a voice-switched command mode, for instance) made the next turns pay a full re-prefill of the new option-list prompt — measured 2.4s vs 0.3s warm on a desktop CPU, and worse: on hybrid-memory models like LFM2.5, whose state cannot be partially rewound (llama.cpp can only restore checkpoints), *every* probe change re-prefilled from scratch whenever the last checkpoint missed the probe boundary, so even same-list turns intermittently cost full prefills. Registering an option list (pipeline seed or session.update) now fires a best-effort background prewarm: two throwaway scores with distinct probes. The first prefills the new option-list prompt; the second, diverging exactly where per-turn probe text starts, plants the backend's rewind point (KV checkpoint) at the stable-prefix boundary that every real turn reuses. The prewarm hides behind the canned mode-switch reply — by the time it finishes speaking, the cache is warm. Idempotent per option set, detached from the registering request's lifetime. Measured on the drone demo (LFM2.5-1.2B, desktop CPU): first turn after a mode switch 2374ms -> 340ms; intermittent same-list full prefills (1.3-2.1s) all -> under 0.5s. For clients that swap lists frequently, options: [parallel:2] on the scoring model additionally keeps one slot per list via prefix-similarity routing (+26MB RSS, unified KV). Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * perf(llama-cpp): checkpoint scoring at the caller-declared stable prefix Hybrid-memory models (LFM2.5 shortconv, Qwen3.5 deltanet — where new small models are headed) cannot rewind their state, so any prompt-cache reuse that needs a rewind falls back to a full re-prefill. For classifier scoring that meant every probe change re-processed the whole option-list prompt: the server's checkpoints were placed reactively (at wherever the previous task happened to diverge), so a checkpoint past the next divergence was erased rather than restored — measured as intermittent 2-10s turns on prompts with a 95%+ common prefix. The classifier now computes the probe-invariant prompt prefix once (the byte-wise common prefix of two synthetic probe renders) and declares its length with every Score request; the server maps it to a token boundary and forces a KV checkpoint exactly there on each score prefill. That checkpoint sits at or before every future divergence under the same option list, so it always survives and always restores — repeat scoring costs probe+candidates regardless of how the probe changes. Also: - prewarm reruns on every option-list registration instead of memoizing per list: with boundary checkpoints a redundant rewarm costs two probe-sized decodes, while skipping one after a slot eviction (three lists sharing fewer slots evict in LRU cascades) silently moves a full re-prefill onto the user's next turn - new llama.cpp backend option rs_seq:N exposes bounded recurrent-state rollback outside speculative decoding; measured impractical for deltanet-scale states (65GB for 64 snapshots on Qwen3.5-4B) but cheap insurance for small-state models - docs: the multi-list recipe (parallel:N + sps:0.5 — the default slot similarity threshold funnels distinct lists onto one slot) Measured on the drone demo (LFM2.5-1.2B scorer, desktop CPU), steady state: every turn 285-421ms including mode switches, vs 2.4s post-switch and intermittent 1.3-2.9s re-prefills before. Assisted-by: Claude:claude-fable-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(realtime): align classifier cache guidance Document the single-score prewarm behavior and clean the vendored score patch formatting. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(llama-cpp): guard score task for fork backends TurboQuant and Bonsai reuse the primary gRPC server against llama.cpp forks that do not carry LocalAI's slot-based Score patches. Compile the Score integration only for the patched primary backend and return UNIMPLEMENTED from fork builds instead of referencing absent task types and common_params fields. Assisted-by: Codex:gpt-5 [gh] Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(dev): generate gRPC code before commit lint The coverage phase regenerates ignored protobuf bindings, but lint runs first and can fail against missing or stale output. Generate the pinned bindings before lint so the gate always type-checks the current schema. Assisted-by: Codex:gpt-5 Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
walcz-de
|
4b4faa4ac7 |
feat(cloud-proxy): optional Anthropic prompt-cache breakpoints in translate mode (#11158)
The Anthropic translate provider builds the upstream request from scratch and
never emitted cache_control, so prompt caching was impossible for OpenAI-format
clients routed through cloud-proxy — even though the entire system prompt + tools
prefix is re-sent on every agentic turn.
Add an opt-in cache_prompt flag (ProxyOptions.cache_prompt; model YAML
proxy.cache_prompt: true). On a translate+anthropic model, buildAnthropicRequest
injects cache_control:{type:ephemeral} on the stable prefix — the system block,
the last tool, and the last message block (at most 3 of Anthropic's 4 allowed
breakpoints). Anthropic then serves the repeated prefix at the cache-read rate
(0.1x input) on subsequent calls, cutting cost on multi-turn/agentic workloads.
No effect in passthrough mode, for non-Anthropic providers, or when unset.
System is widened to any so it can carry the block form required to attach
cache_control, while still marshalling as a bare string when caching is off.
Adds a unit test asserting exactly three breakpoints when on and none when off,
and documents the option in docs/content/operations/cloud-proxy.md.
Assisted-by: Claude:opus-4.8
Signed-off-by: stefanwalcz <stefan.walcz@walcz.de>
|
||
|
|
2d889e61a6 |
feat(backend): add magpie-tts-cpp text-to-speech backend (#11115)
* feat(backend): add magpie-tts-cpp text-to-speech backend
Add a Go + purego backend wrapping the magpie-tts.cpp ggml port of NVIDIA's
Magpie TTS Multilingual 357M (encoder + autoregressive decoder over NanoCodec
tokens), producing 22.05 kHz mono audio in 5 baked voices (Aria, Jason, John,
Leo, Sofia; case-insensitive names or indices 0-4) across 9+ languages from a
single self-contained GGUF. Mirrors qwen3-tts-cpp / moss-tts-cpp: dlopen the
static-ggml shared library, bind the flat magpie_tts_capi_* C-API via purego
(no local C shim needed, the upstream .so exports it directly), and serve the
gRPC TTS + TTSStream methods behind base.SingleThread (the C context is not
reentrant across synthesize calls).
The backend CMakeLists translates the Makefile's -DGGML_{CUDA,METAL,VULKAN,HIP}
flags into upstream's MAGPIE_GGML_* toggles (upstream FORCE-overwrites the ggml
cache entries from those), pinned to magpie-tts.cpp v0.1.1
(e3f3dd1ebe22b64e7405f93b519f2d1930712568), which statically links ggml into
libmagpie-tts.so (ldd shows only system libs).
Wires the full registration: backend-matrix.yml (CPU amd64/arm64, CUDA 12/13,
Intel SYCL f16/f32, Vulkan amd64/arm64, ROCm, NVIDIA L4T + L4T CUDA 13, and
Darwin metal), backend/index.yaml metas and image entries, the root Makefile
build targets, the changed-backends backend-filter path mapping, the bump_deps
auto-bump matrix, a test-extra per-backend smoke job, the /backends/known
pref-only importer entry, the backend capabilities map (TTS + TTSStream, no
voice cloning), and the README / compatibility-table docs rows.
Verified locally: unit + e2e Ginkgo suites pass against the real q8_0 GGUF
(22.05 kHz mono WAV, RMS > 0.01), a live gRPC LoadModel + TTS round-trip
returns valid non-silent audio, and the pre-commit gates (make lint,
make test-coverage-check) pass, run manually with LOCALAI_TEST_HTTP_PORT
overriding the locally-occupied 9090.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* gallery: add magpie-tts-cpp model entries (q8_0 + f16)
Add the Magpie TTS Multilingual 357M GGUFs from mudler/magpie-tts.cpp-gguf to
the model gallery: q8_0 (~624 MB, near-lossless, fastest decode, recommended)
with an f16 (~784 MB) variant, both served by the magpie-tts-cpp backend.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* magpie-tts-cpp: bump pin to rewritten upstream v0.1.1 SHA
Upstream history was rewritten to purge accidentally committed build
artifacts; v0.1.1 now resolves to 6f7696cf.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
2fe10c3c4a |
fix(model-artifacts): persist companion artifacts so remote workers get the base_model option (#11075)
fix(model-artifacts): persist companion artifacts, not just the primary
A managed model can declare companion artifacts (LongCat-Video-Avatar-1.5
pulls its tokenizer, text encoder and VAE from the separate LongCat-Video
base repo via a target: companion artifact). preloadOne resolves the whole
set in memory, but the binding written back to disk carried only the
primary: persistArtifactBinding marshalled []Spec{result.Spec} and replaced
the entire artifacts: list with it, silently dropping every companion.
In a single process the loss is invisible because the in-memory config keeps
the companion. It bites on the next controller restart: the config reloads
from the mangled file with the primary alone, so withCompanionArtifactOptions
finds no resolved companion and synthesizes no base_model option. The remote
longcat-video backend then never receives base_model, falls back to
BASE_MODEL_ID and downloads the repo itself ("Downloading required files for
meituan-longcat/LongCat-Video"), failing the load with "base_model must point
to a LongCat-Video checkpoint".
This is why an explicit base_model:<path> added to the config options works
where the managed companion does not: an explicit option lives in options:,
which is never rewritten, while the managed companion lives in artifacts:,
which the binding overwrote.
Persist the full resolved set (primary + every companion), and widen
bindingNeedsPersistence to compare the whole artifact list so a companion
resolving for the first time still triggers a write. The single-node path is
unaffected: there the in-memory config already carried the companion, and the
staging/ModelPath resolution for a remote worker (nested per-model staged
root, #10949) is unchanged and already correct once the option is generated.
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
6584db992f |
fix(nodes): never schedule a model onto a node that cannot store it (#11054)
* fix(nodes): never schedule a model onto a node that cannot store it
A worker whose models filesystem was 100% full kept advertising
`status: healthy`, stayed a scheduling candidate, was picked to host a
70 GB video model, accepted the staging request, transferred ~17 GB and
only then failed:
staging .../whisper-large-v3/model.fp32-00001-of-00002.safetensors:
upload to node b7bacbf4-... failed with status 500:
writing file: /models/longcat-video-avatar-1.5/...: no space left on device
The node was at 937G/937G/0-avail. Total elapsed before the truth
surfaced: 16 minutes, for a decision that could never have succeeded.
The worker health signal only ever proved liveness. `/readyz`
(WorkerReadiness/NATSReadiness) checks the NATS link; `status: healthy`
in the registry is driven by heartbeat recency. Node capacity carried
VRAM and RAM but no disk figure at all, and the router compared model
size against VRAM only — nothing anywhere looked at free space on the
filesystem that staging actually writes to.
Report it, then use it:
- Workers now measure the filesystem backing their MODELS directory
(not `/` -- staged weights land in the models path, and that mount is
very often separate) and report `total_disk`/`available_disk` on
registration and on every heartbeat. Free disk moves faster than VRAM
under staging traffic, so the per-heartbeat refresh matters.
- The SmartRouter drops nodes that cannot store the model before it
picks one. The requirement comes from `modelPayloadBytes` -- the same
local paths `stageModelFiles` uploads, already computed for the
size-derived load budget -- plus a 5% / 1 GiB margin, rather than a
fixed percentage of the node's disk. A percentage threshold would take
a small-but-usable node out of rotation for models it could hold, and
on a homogeneous cluster would strand every node at once.
- When no node fits, scheduling fails immediately with an error naming
the requirement and each node's free space, instead of picking one and
discovering it mid-transfer.
Two deliberate non-changes. Low disk does not mark a node `unhealthy`:
the check is per model, so a node too small for one model stays a valid
target for smaller ones. And `total_disk == 0` means "does not report
disk" (pre-upgrade worker, or a failed stat), not "full" -- such nodes
pass through untouched so a rolling upgrade never empties the candidate
pool. A genuinely full node is distinguishable: non-zero total, zero
available. Registry read failures are logged and scheduling continues
unfiltered; a database hiccup must not wedge a cluster.
Free space is surfaced on the node detail page next to VRAM, since the
incident's signature was a node that looked entirely healthy.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
* feat(nodes): make the disk-headroom check operator-controllable
The admission check added in the previous commit had no off switch. A
scheduler-side veto with no escape hatch is a liability: our size
estimate can be wrong (deduplicating or compressing filesystems, a
backend that fetches its own weights rather than loading the staged
copy), and an operator who hits that has no way out but a downgrade.
Add one knob with two surfaces that share a single source of truth:
- `--distributed-disk-headroom-check` / `LOCALAI_DISTRIBUTED_DISK_HEADROOM_CHECK`
(default true), following the `--distributed-prefix-cache` pattern for
a default-on distributed feature.
- `distributed_disk_headroom_check` in the runtime-settings registry, so
it can be flipped without a restart from `POST /api/settings` and from
Settings -> Distributed in the WebUI.
Both write `DistributedConfig.DiskHeadroomDisabled`, and the SmartRouter
reads that member LIVE on every scheduling decision through a closure
over the application config rather than a value snapshotted at
construction. Env/CLI sets the boot value, the runtime setting overrides
it live, last write wins, and there is exactly one member to read.
Snapshotting would have made the runtime toggle a no-op until restart.
Disabled means WARN, not SKIP. Selection goes back to ignoring free disk
-- byte for byte the pre-check behaviour -- but the check still runs, and
when it would have rejected every node it says so, naming the knob that
suppressed it. Going quiet when switched off would reproduce the exact
condition that made the original incident expensive: a cluster doing
something that could not work and saying nothing. Disabling is also
logged once at startup. Warning only on the total-rejection case keeps
it actionable rather than chatty on a heterogeneous cluster.
Also fixes a false positive in the check itself: shared-models mode
(LOCALAI_DISTRIBUTED_SHARED_MODELS) stages nothing at all -- every node
already mounts this models directory at this path -- so demanding the
full checkpoint size of free space per node would have rejected a
cluster that needs no new bytes. The check is skipped there entirely.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
ff299df453 |
perf(http): gzip responses, cache hashed assets, bound the trace endpoints (#11056)
Three measured HTTP-layer regressions on a live deployment, fixed together
because they all shape the bytes on the wire.
1. No compression. The server sent no Content-Encoding regardless of what
the client asked for, confirmed with curl straight at 127.0.0.1:8080 so
it was not an ingress artefact. Adds gzip middleware, on by default and
configurable via LOCALAI_DISABLE_HTTP_COMPRESSION and
LOCALAI_HTTP_COMPRESSION_MIN_LENGTH (default 1024 bytes so tiny bodies
are not wastefully wrapped). Streaming routes are skipped explicitly:
an SSE Accept header, a WebSocket upgrade, and the completion / SSE /
log-tail path prefixes, because whether a completion request streams is
decided by the request body, which the middleware runs too early to see.
Already-compressed formats (woff2, png, mp4, ...) are skipped too; gzip
made those marginally larger. Measured over the embedded React build:
JS+CSS 2815 KB raw to 808 KB gzipped (3.48x).
2. No cache headers on content-hashed assets. Vite hashes the filenames,
so a given /assets/ URL can never change content, yet they shipped with
no Cache-Control, ETag or Last-Modified, and the browser re-fetched the
whole bundle on every navigation with no conditional request available.
/assets/* now carries public, max-age=31536000, immutable. index.html
stays no-cache so a deploy is picked up, and the unhashed locale JSONs
get a short TTL rather than the immutable one.
3. Unbounded trace endpoints. /api/traces returned 21,033,606 bytes in
4.65s and /api/backend-traces 3,471,682 bytes in 1.50s, and the admin
UI polls both every few seconds. The ring buffer holds up to 1024
entries, each embedding full input_text payloads. Both list endpoints
now take limit / offset / full, default to 50 entries, and strip the
heavy fields (request and response bodies plus headers for API traces,
body and data for backend traces) unless full=true. Every trace gets a
process-lifetime ID and GET /api/traces/{id} and
/api/backend-traces/{id} serve the full record, which is what the UI
fetches when a row is expanded. The list body stays a JSON array;
paging metadata rides in X-Total-Count, X-Trace-Offset and
X-Trace-Limit. Reproducing the live shape in a test, the polled payload
goes from 21,131,097 bytes to 7,201 bytes.
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>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
01fca9c9b2 |
fix(distributed): scale the remote model-load deadline with checkpoint size (#11030)
The gRPC deadline for the remote LoadModel call was a fixed 5m. It starts
only after the backend install and file staging have completed, so it
covers the worker's checkpoint read and pipeline init alone - work whose
duration is proportional to the bytes on disk. A fixed value is therefore
a model-size cliff, not a timeout.
Measured in production: a 70 GB video checkpoint (longcat-video-avatar-1.5)
on an NVIDIA Jetson Thor worker failed reproducibly with
"rpc error: code = DeadlineExceeded" after 953.5s of wall clock. Backend
install plus staging consumed ~11m, then LoadModel got its 5m and expired.
The load never had a chance, and the operator saw only a generic
DeadlineExceeded with no hint that a config value was the cause.
Raising the constant does not fix this. It moves the cliff to the next
larger model - the cluster has to support 600 GB checkpoints - and it makes
a genuinely wedged SMALL model hang for the whole inflated duration before
anyone notices, which is a real regression in failure latency.
So derive the budget from the checkpoint size instead:
budget = 5m + 20s/GiB, capped at 6h
2 GiB -> 5m40s, 70 GiB -> 28m20s, 600 GiB -> 3h25m. The per-GiB rate is
deliberately pessimistic (~54 MB/s of weight read) because the errors are
not symmetric: too long costs only failure latency on a load that was going
to fail anyway, too short is a guaranteed false failure on a healthy load.
The size is measured from the frontend's local model files, over the same
path set stageModelFiles uploads. When those files are not present locally -
a backend handed a bare HuggingFace repo id fetches its own weights on the
worker - there is nothing to measure and the budget stays at today's 5m.
An explicit LOCALAI_NATS_MODEL_LOAD_TIMEOUT still wins outright, in both
directions: a shorter override is honoured, so an operator who wants fast
failure is not silently extended by the heuristic.
The cold-load hold needed widening to match. It extends on staging progress,
but LoadModel reports none, so once the last byte lands the hold expires a
stall window later and would cancel a load still well inside its own budget.
scheduleAndLoad now extends the hold by the load budget plus the staging
margin as it enters the load phase; ModelLoadCeilingFor stays the hold's
starting budget rather than its maximum.
Finally, a deadline that does expire now names the budget, the checkpoint
size it was derived from, and the knob that overrides it, instead of
surfacing a bare "context deadline exceeded".
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
2f33ad6669 |
fix(modelartifacts): treat CIFS EACCES as lock contention, not failure (#10986)
flock(2) on CIFS/SMB returns EACCES when another client holds the lock: the kernel maps STATUS_LOCK_NOT_GRANTED and STATUS_FILE_LOCK_CONFLICT to -EACCES and never produces EWOULDBLOCK on that path. gofrs/flock only recognises EWOULDBLOCK as contention, so TryLockContext returned a bare "permission denied" and Ensure aborted. Both replicas then fell back to legacy loading, which makes the worker download the whole repo in-band inside LoadModel and blow the remote-load deadline. Replace TryLockContext with an explicit wait loop over a new Locker interface, classifying EWOULDBLOCK/EAGAIN/EACCES/EBUSY as contention. EACCES is ambiguous at the syscall boundary but not here: the lock file is already open O_CREATE|O_RDWR, so a real permission problem would have failed the open with an *fs.PathError, and flock(2) documents no EACCES on Linux at all. The wait is bounded (DefaultLockWait, overridable via WithLockWait), so even a misclassification degrades to a delay. On timeout the committed result is re-checked before reporting the new ErrLockContended, so a peer that finished the work still wins. Locker also exists so the contention path is testable without a network filesystem: nothing in CI can make flock(2) return EACCES on demand. Raise the fallback to error for a managedArtifactBackends backend, via a shared config.LogArtifactFallback used by both call sites. For those backends the legacy path is not graceful degradation, and the operator otherwise sees only a timeout with no causal link. The fallback stays non-fatal. Drop the os.Chmod(layout.Lock, 0o600) after acquisition: flock.New already creates the file 0600, and the chmod was gratuitous risk on a nounix mount that ignores modes. Fixes #10981 Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Nandana Dileep
|
b5e4413eab |
feat: add MiniMax-M3 model support (#10837)
Adds inference parameter defaults for the minimax-m3 model family and includes a vendored patch of upstream llama.cpp PR #24523 to recognize the minimax-m3 architecture. Once the upstream PR merges, the patch can be removed and LLAMA_VERSION bumped normally. Changes: - backend/cpp/llama-cpp/patches/0001-add-minimax-m3-support.patch: vendored patch from ggml-org/llama.cpp#24523 (Preliminary MiniMax-M3 support). Applied by prepare.sh during the build; keeps the pinned LLAMA_VERSION pointing at the latest upstream tag. - core/config/inference_defaults.json: add minimax-m3 family entry (temperature=1.0, top_p=0.95, top_k=40, min_p=0.01, repeat_penalty=1.0, matching the existing minimax defaults) and register it in the patterns list before the shorter minimax-m2.7 entry for correct longest-match-first ordering. Upstream: depends on ggml-org/llama.cpp#24523 Closes: https://github.com/mudler/LocalAI/issues/10820 Signed-off-by: Nandana Dileep <110280757+nandanadileep@users.noreply.github.com> |
||
|
zjuzhongwen
|
864c84f48b |
chore: fix some comments to improve readability (#10960)
Signed-off-by: zjuzhongwen <zjuzhongwen@outlook.com> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
0e0221b0f5 |
fix(vision): probe the media marker for pinned llama.cpp backend variants (#10955)
llama.cpp picks a random per-process media marker (ggml-org/llama.cpp#21962),
so LocalAI renders the prompt with a "<__media__>" sentinel and swaps in the
backend's real marker after probing ModelMetadata.
That probe was gated on an exact match against "llama-cpp", the gallery's meta
backend name. A model config pinning a concrete build ("vulkan-llama-cpp",
"cuda12-llama-cpp", "rocm-llama-cpp", ... and their -development counterparts)
runs the same llama.cpp gRPC server but skipped the probe, so MediaMarker
stayed empty, no substitution happened, and the prompt reached mtmd still
carrying the sentinel. mtmd_tokenize then counted zero markers against one
bitmap and every image request failed with "Failed to tokenize prompt".
The same early return also skipped thinking-mode detection and tool-format
marker extraction, so a pinned variant silently lost reasoning and native
tool-call parsing too.
Add IsLlamaCppBackend, which recognises the whole variant family (plus the
empty auto-detect name, which resolves to llama.cpp) while excluding
ik-llama.cpp, a separate engine that merely shares the suffix.
Fixes #10945
Assisted-by: Claude Code:claude-opus-4-8[1m] [Read] [Edit] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
fb4c61d1c9 |
fix(distributed): configurable remote model-load timeout, and reap the load when it times out (#10948)
* fix(distributed): make the remote LoadModel deadline configurable
The router hardcoded a 5 minute gRPC deadline for the remote LoadModel
call. Staging finishes before the timer starts, so those five minutes
cover only the worker backend's own checkpoint load and pipeline init.
A cold load of meituan-longcat/LongCat-Video-Avatar-1.5 (~83 GB) on an
ARM64 Thor worker fails at exactly 302s with DeadlineExceeded while the
backend process is still making progress (CPU time accumulating, RSS
moving as weights are mapped), so the load was cut short rather than
wedged.
Add LOCALAI_NATS_MODEL_LOAD_TIMEOUT / --model-load-timeout mirroring the
existing backend-install timeout knob, defaulting to 5m so unset
clusters keep today's behaviour.
The cold-load hold ceiling (which bounds how long one load may hold the
per-model advisory lock) was derived from the install timeout alone, so
raising the load deadline past it would have been silently clipped.
Derive it from both budgets via ModelLoadCeilingFor:
max(install + load + 5m staging margin, 25m)
With the defaults that is 15m + 5m + 5m = 25m, identical to the previous
constant, and the 25m floor means shrinking either budget can never
tighten the ceiling below what clusters relied on before.
Assisted-by: Claude:claude-opus-4-8 golangci-lint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(distributed): reap the abandoned replica when a remote load times out
The gRPC deadline on the remote LoadModel call only cancels the client
side. A backend blocked in a synchronous weight load never observes its
cancelled handler context, so when scheduleAndLoad gave up it left the
worker loading with nobody waiting for the result.
Observed on an ARM64 Thor worker loading LongCat-Video-Avatar-1.5: the
client returned DeadlineExceeded at 302s, and the backend process was
still alive 30 minutes later having pulled ~57GB from HuggingFace. Every
retry stacked another multi-GB loader on the worker; they had to be
reaped by hand via POST /api/nodes/:id/models/unload.
Send backend.stop for the exact `modelID#replicaIndex` process key we
just abandoned. The exact key matters: a bare model ID stops every
replica on that node, including healthy ones serving traffic.
Only a deadline or cancellation triggers the reap. Any other LoadModel
failure is the backend answering, which means its handler returned and
the process is idle - stopping it there would discard a warm process and
its downloaded weights. The reap is best-effort and never replaces the
load error the caller is waiting on.
The `modelID#replicaIndex` format was already hand-rolled in two places
(the worker's buildProcessKey and pkg/model's log store). Rather than add
a third, export model.BackendProcessKey from pkg/model, the lowest common
dependency of both sides.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 golangci-lint
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
626ae4d51e |
fix(model-artifacts): materialize longcat-video on the controller, and support companion repos (#10949)
* fix(model-artifacts): materialize longcat-video checkpoints on the controller longcat-video loads a checkpoint directory: its backend.py takes request.ModelFile when os.path.isdir(request.ModelFile) and otherwise falls back to snapshot_download. That places it in the same class as transformers/vllm/diffusers/sglang, but the allow-list added in #10910 did not enumerate it, so PrimaryArtifactSpec returned no managed artifact for a bare HuggingFace repo id. The consequence in distributed mode: nothing was acquired on the controller, ModelFileName fell through to the raw repo id, and staging skipped the resulting phantom /models/<owner>/<repo> path. The worker received a blank ModelFile, fell back to request.Model, and downloaded ~83GB from HuggingFace inside the remote LoadModel deadline - so the load could only ever fail with DeadlineExceeded while an abandoned backend process kept downloading. Note this materializes the full repository. The backend restricts its own snapshot_download with allow_patterns, and the avatar repo ships both base_model/ and base_model_int8/ where only one is ever loaded; inferred specs have no way to carry patterns today. Tracked separately. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): warn when staging skips a non-existent model path stageModelFiles logs "Staging model files for remote node" up front, then silently drops any path field that does not exist on the controller. The skip itself is legitimate and must stay: a backend outside managedArtifactBackends that takes a bare HuggingFace repo id gets an optimistically constructed path (ModelFileName falls through to the raw model reference) that was never materialized, and sources its own weights on the worker. Erroring would break those configs. But at debug level the operator is left with a reassuring staging line and no trace of the skip, so a genuine controller-side acquisition gap is indistinguishable from a healthy pass-through - it surfaces much later as a remote LoadModel timeout, on a worker that is quietly downloading tens of gigabytes. Raise the skip to warn and name the field, path, node and tracking key. Behavior is unchanged. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(model-artifacts): allow a config to declare companion artifacts A composed pipeline needs more than one HuggingFace snapshot. LongCat-Video-Avatar-1.5 loads its own transformer but takes the tokenizer, text encoder and VAE from the separate LongCat-Video base repo, so a single-artifact config cannot express it and the backend is left to fetch the second repo itself at load time. Widen the artifact model to target: model plus any number of named target: companion entries. Normalize accepts the new target and constrains a companion name to [a-z0-9][a-z0-9_-]{0,63} because that name is the option key the backend later receives; a companion may not claim primary_file, which only means anything for a load target. ModelConfig.Validate requires exactly one primary and requires it first, since Artifacts[0] is what ModelFileName, size estimation and staging all resolve from. Both acquisition paths now loop instead of touching index 0 alone: preloadOne for an already-installed config, bindPrimaryArtifact for a gallery install. Failure policy differs by provenance. An inferred primary keeps its warn-and-fall-back, because the legacy download path still exists for it. Companions are explicit by construction, so they are all-or-nothing: a config naming one is asserting the backend needs it, and failing at the acquisition boundary is far more legible than a missing-weights error surfacing later inside the backend. The cache key is deliberately unchanged. It hashes source identity only, never name or target, so every already-installed managed model still hits its existing snapshot instead of silently re-downloading. Two specs pin that: one proving a companion and a primary with identical sources agree on the key, and one pinning the digest of a known primary outright. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(model-artifacts): hand resolved companion snapshots to the backend A materialized companion is useless until the backend can find it, and its location is a content-addressed cache key that does not exist until the artifact resolves. A static gallery override cannot carry that, and persisting it into the config YAML would rot the moment a re-resolve produced a new key. Synthesize it instead at load time: each resolved companion becomes "<artifact name>:<snapshot path>" in ModelOptions.Options, reusing the key:value convention backends already parse for options like attention_backend. The value stays relative to the models directory so a remote worker can resolve it under its own ModelPath once staging has rewritten the model root. An option the author set explicitly always wins, so pinning a companion to a local checkout still beats the managed snapshot. longcat-video resolves base_model through ModelPath, the same convention qwen-tts, voxcpm, outetts and ace-step already use for companion assets. Its sibling-directory heuristic is deleted: it looked for a LongCat-Video directory next to the model, which cannot exist under the content addressed .artifacts/huggingface/<key>/snapshot layout, so it was dead code the moment the model became managed. The gallery entry declares both repositories and restricts each with allow_patterns. The avatar repo ships base_model/ and base_model_int8/ and only ever loads one, so fetching the whole repo would roughly double the download. The patterns match the entry's own options (use_distill true, use_int8 default false); enabling use_int8 here also requires adding base_model_int8/**, which is called out in the entry. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(distributed): stage managed artifact trees from the models root Staging anchored the worker's models directory on the primary snapshot whenever a model was managed, so a companion snapshot could not reach the worker at all. frontendModelsDir was derived by stripping the Model relative path off the end of ModelFile. For a managed artifact nothing matches: ModelFile is .artifacts/huggingface/<key>/snapshot while Model stays a bare HuggingFace repo id, so the strip was a no-op and the "models directory" came out as the snapshot itself. Two consequences, both silent. Staging keys lost the .artifacts/huggingface/<key>/snapshot prefix, so two snapshots of one model were indistinguishable on the worker. And a companion, which lives in a sibling snapshot directory outside the primary, fell outside that directory entirely: StagingKeyMapper.Key collapsed its files to bare basenames and resolveOptionPath could not resolve the relative option at all, so it was skipped without a word. Derive the models root from the artifact tree instead when the path runs through it, and compute the worker's ModelPath from the file's path relative to that root rather than from the Model field. The legacy layout is unaffected: where Model really is the relative path, the new derivation reduces to the old one, which a regression spec pins. This deliberately changes an invariant that router_dirstage_test.go pinned: for a managed primary, ModelFile and ModelPath were both the snapshot directory, and staging keys were relative to it. Now ModelFile is the snapshot, ModelPath is the models root above it, and keys keep the full relative path. That spec is updated rather than accommodated, with the reasoning recorded inline, because the old invariant is exactly what made a sibling companion unreachable. Assisted-by: Claude:opus-4.8 [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> |
||
|
mudler's LocalAI [bot]andEttore Di Giacinto
|
2dade4a9f9 |
fix(model-artifacts): gate inferred artifact materialization by backend (#10910)
The managed-artifact materializer stages a HuggingFace snapshot into a directory (.artifacts/huggingface/<key>/snapshot/). That is the right load target for directory-consuming backends (transformers, vLLM, diffusers, ...), but PrimaryArtifactSpec inferred a managed artifact from ANY HuggingFace-shaped model reference regardless of backend. A single-file backend such as llama.cpp or whisper was therefore handed the snapshot directory instead of the weight file and failed to load it. The /import-model importer already guards this with a backend allow-list (managedArtifactBackends), but the loader-side inference did not. Move the allow-list into core/config as IsManagedArtifactBackend and apply it in PrimaryArtifactSpec: only directory-consuming backends may have an artifact inferred from a bare reference; every other backend stays on the legacy download-to-file path. An explicit artifacts: block still bypasses the gate, where single-file snapshot resolution handles the load path. The importer now shares the same predicate, so both paths agree on which backends auto-materialize. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
localai-org-maint-botandEttore Di Giacinto
|
279f5b8a93 |
fix(model-artifacts): load single-file HF snapshots from the file, not the directory (#10909)
fix(model-artifacts): load single-file HF snapshots from the file, not the dir The managed Hugging Face artifact materializer (#10825) always pointed backends at the snapshot *directory* (.artifacts/huggingface/<key>/snapshot). For a single-file model reference such as huggingface://nomic-ai/nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf, the GGUF lives *inside* that directory, so llama.cpp was handed a directory and failed with "gguf_init_from_reader: failed to read magic". This has kept the tests-aio job red on master since the feature merged (the embeddings e2e tests could not load text-embedding-ada-002). Record the single file of a one-file snapshot as Resolved.PrimaryFile and have ModelFileName() resolve to snapshot/<PrimaryFile> when it is set. Multi-file snapshots (e.g. transformers repos consumed as a directory) keep pointing at the snapshot directory. PrimaryFile is derived from the resolved contents and is deliberately excluded from the artifact cache key. estimateModelSizeBytes now derives the snapshot directory from the cache key instead of ModelFileName(), so its manifest lookup is unaffected by the file-vs-directory resolution. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
c1a891662c |
refactor(settings): single declarative registry for runtime settings (fixes the #10845 bug class) (#10864)
* feat(settings): add declarative runtime-settings field registry One fieldSpec row per RuntimeSettings field, with a reflection completeness spec so a field added without a registry row is a red test instead of a silently-dropped setting (the #10845 bug class). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-fable-5 * refactor(settings): drive ToRuntimeSettings/ApplyRuntimeSettings from the field registry Behavior-preserving: ~350 hand-written per-field lines become two loops over runtimeSettingsFields, gated by a To->Apply->To round-trip spec. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-fable-5 * feat(settings): baseline-driven startup merge for persisted runtime settings ApplyRuntimeSettingsAtStartup compares the live config against DefaultRuntimeBaseline (option-less-run defaults incl. kong-injected flag defaults) instead of per-field == 0 guards. Fixes persisted lru_eviction_max_retries, tracing_max_items, agent_job_retention_days, memory_reclaimer_threshold, galleries and autoload flags being silently ignored at boot. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-fable-5 * fix(settings): registry-driven startup merge, applied before consumers loadRuntimeSettingsFromFile becomes a thin wrapper over ApplyRuntimeSettingsAtStartup and runs at the top of New(), before model configs capture app-level defaults. WithThreads stops eagerly resolving 0 so a persisted thread count survives restart while LOCALAI_THREADS still wins (#10845); the physical-core fallback moves after the merge. Also: run.go now injects the memory-reclaimer threshold unconditionally so the option-less boot matches DefaultRuntimeBaseline and a UI-saved threshold survives restart. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-fable-5 * refactor(settings): file watcher delegates to the registry merge; shared API-key merge Manual edits to runtime_settings.json now behave like a boot-time load (env still wins) instead of the inverted diverged-from-startup guard that ignored most manual edits. MergeAPIKeys dedups env keys in one place for the endpoint and the watcher. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-fable-5 * docs(settings): document unified runtime-settings precedence Document the single env/CLI > runtime_settings.json > defaults rule, applied identically at boot, on POST /api/settings, and on manual file edits, plus the two known limitations (default-valued env vars are indistinguishable from unset; API-changed fields hot-apply on the next restart only). Also add a completion debug log when the watcher applies runtime_settings.json. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-fable-5 * test(settings): reset the global VRAM cap leaked by the round-trip spec The round-trip spec applies vram_budget=12GiB, whose post-loop hook installs a process-global default cap; without a reset every spec ordered after it runs under that phantom budget. Also drop a stale enumeration in the ApplyRuntimeSettings doc comment. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude Code:claude-fable-5 --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
8cec22c3b7 |
feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)
* feat(vram): add vrambudget primitive for per-node VRAM caps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): apply default VRAM budget in xsysinfo aggregate getters Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): wire LOCALAI_VRAM_BUDGET flag to xsysinfo default budget Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): persist VRAM budget via runtime settings with live apply Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(vram): reset process-global VRAM budget after runtime-settings spec Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add VRAM budget field to Settings page Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): store and enforce per-node VRAM budget in the node registry Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): apply per-node VRAM budget in router hardware defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): report worker VRAM budget in node registration The distributed worker now reports its operator-set VRAM budget string (LOCALAI_VRAM_BUDGET) to the server on registration. The worker keeps reporting RAW total/available VRAM and never sets the xsysinfo process-global budget (that stays standalone-only); the server resolves and enforces the budget uniformly (Task 6). Also closes a Task 6 gap: on re-registration, a struct Updates zero-skips an empty budget, so a worker that dropped LOCALAI_VRAM_BUDGET left the stale cap in place. For non-admin-override nodes the budget columns are now force-written (map Updates) even when empty, so removing the env var clears the cap; admin overrides are preserved unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(vram): drop em dash from worker-clear comment Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add node VRAM budget admin endpoints Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): add node VRAM budget control to the node UI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(vram): expose set_node_vram_budget MCP admin tool Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(vram): document LOCALAI_VRAM_BUDGET and node VRAM budget UI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(vram): avoid double-applying VRAM budget in GetResourceAggregateInfo The GPU-branch aggregate returned by GetResourceInfo is sourced from GetGPUAggregateInfo, which already caps total/free/used against the process-wide VRAM budget. GetResourceAggregateInfo then applied the budget a second time. For an absolute budget this is idempotent, but for a percentage budget b.Apply resolves the ceiling as a fraction of its input total, so a second pass yields P*(P*T) instead of P*T and distorts UsagePercent (read by the memory reclaimer in pkg/model/watchdog.go). Remove the redundant second application so the budget is applied exactly once, against the raw physical totals, upstream in GetGPUAggregateInfo. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(vram): implement SetNodeVRAMBudget on mcp assistant test stub The LocalAIClient interface gained SetNodeVRAMBudget; the stubClient in core/http/endpoints/mcp used by the assistant tests is a separate implementer and needs the method too (broke golangci-lint typecheck and both test jobs). 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
bcc41219f7 |
feat: materialize Hugging Face model artifacts (#10825)
* feat(config): add model artifact source contract Assisted-by: Codex:GPT-5 [Codex] * feat(downloader): add authenticated raw-byte progress Assisted-by: Codex:GPT-5 [Codex] * feat(huggingface): resolve immutable snapshot manifests Assisted-by: Codex:GPT-5 [Codex] * feat(models): add artifact storage primitives Assisted-by: Codex:GPT-5 [Codex] * feat(models): materialize pinned Hugging Face snapshots Assisted-by: Codex:GPT-5 [Codex] * feat(models): bind managed snapshots at runtime Assisted-by: Codex:GPT-5 [Codex] * feat(gallery): materialize model artifacts during install Assisted-by: Codex:GPT-5 [Codex] * feat(gallery): declare managed Hugging Face artifacts Assisted-by: Codex:GPT-5 [Codex] * feat(models): preload managed model artifacts Assisted-by: Codex:GPT-5 [Codex] * fix(gallery): retain shared artifact caches on delete Assisted-by: Codex:GPT-5 [Codex] * feat(models): report artifact acquisition progress Assisted-by: Codex:GPT-5 [Codex] * refactor(backends): load managed models from ModelFile Assisted-by: Codex:GPT-5 [Codex] * refactor(backends): load staged speech model snapshots Assisted-by: Codex:GPT-5 [Codex] * refactor(backends): use staged snapshots in engine backends Assisted-by: Codex:GPT-5 [Codex] * test(distributed): cover staged artifact snapshots Assisted-by: Codex:GPT-5 [Codex] * docs: explain managed model artifacts Assisted-by: Codex:GPT-5 [Codex] * docs: add product design context Assisted-by: Codex:GPT-5 [Codex] * feat(ui): show model artifact download progress Assisted-by: Codex:GPT-5 [Codex] * Eagerly materialize Hugging Face artifacts Materialize HF-backed model references as managed GGUF artifacts during load, with lazy download retained only as fallback. Assisted-by: Codex:GPT-5 [shell] * Refactor HF downloads through a shared executor Assisted-by: Codex:GPT-5 [shell] * drop 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
b224c96db6 |
fix(config): only inject llama.cpp serving options on the llama.cpp path (#10822)
SetDefaults injected the llama.cpp server options cache_reuse (ApplyServingDefaults) and parallel (ApplyHardwareDefaults, re-applied per selected node by the distributed router) onto every model config regardless of backend. Every other backend ignores options it does not understand, so this was harmless until longcat-video, which strictly validates its options and fails LoadModel with "unknown model option(s): cache_reuse, parallel". Gate both injections behind a new UsesLlamaCppServingOptions allow-list (llama-cpp plus the empty/auto-detect case that resolves to llama.cpp from a GGUF file, mirroring how llamaCppDefaults is registered). This follows the existing UsesLlamaSamplerDefaults precedent for llama-only defaults. The typed NBatch field is deliberately left alone: it is a proto field every backend simply ignores, which is why batch never triggered the error. Also harden the longcat-video backend to warn-and-ignore unknown model options and request params through a testable select_known_options helper, matching the other LocalAI Python backends, so a future server-injected option cannot break loading again. 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
4056283aa4 |
[voice] feat: add managed voice cloning profiles (#10799)
* feat(ui): add voice library workflow Give administrators a production-ready flow to record or upload consented reference audio, manage reusable profiles, inspect API usage, discover compatible models, and hand a saved voice directly to text-to-speech. Assisted-by: Codex:gpt-5 * feat(voice): add managed voice cloning profiles Make reusable reference voices manageable through the admin API instead of requiring model-directory and YAML edits. Discover compatible installed and gallery models from server-side backend capabilities, retain explicit model configuration controls, and stage saved references for supported backends. Expose profile management through REST and MCP, document backend-specific behavior, and cover the workflow from profile creation through real Qwen3-TTS synthesis. Harden the agent-job HTTP test against completion racing cancellation. Assisted-by: Codex:gpt-5 --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
b00422e45f |
feat(backends): add LongCat video and avatar generation (#10792)
* feat(backends): add LongCat video and avatar generation Assisted-by: Codex:GPT-5 [apply_patch] [exec_command] [web] * refactor(config): declare model I/O modalities Make model configs declare input and output modalities so capability discovery no longer branches on backend or checkpoint names. Complete the LongCat gallery and user documentation, make the SDPA patch apply to the pinned upstream revision, and stabilize the Agent Jobs race exposed by the required hook. Assisted-by: Codex:GPT-5 [web] --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
5569b2de56 |
feat(config): context_size: -1 to auto-use model's full trained context (#10752)
* feat(config): clamp negative context_size to default in EffectiveContextSize Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(config): resolve context_size=-1 to model trained max with VRAM warn Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * fix(config): treat negative context_size as unset when GGUF is unparseable Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * docs(config): document context_size=-1 auto-max Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * docs(backend): drop em dashes from EffectiveContextSize comment Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
40c29db8c4 |
fix(logs): capture backend logs by default in single mode (#10742)
Backend log capture into the per-model BackendLogStore (which feeds the UI "Backend Logs" page and /api/backend-logs) was opt-in and off by default in single mode, while worker/distributed mode force-enables it via SetBackendLoggingEnabled(true). There was no CLI flag either, so the only way to populate the store was the Settings UI toggle - and the page was silently empty out of the box. Distributed "just worked"; single mode looked broken. Default EnableBackendLogging to true in NewApplicationConfig so single mode matches worker mode. The store is a small in-memory ring buffer, so the cost is negligible. Now that the default is on, loadRuntimeSettingsFromFile's usual "only flip false->true" merge would ignore a persisted false and revert the UI toggle-off on every restart. There is no env var/CLI flag for this setting, so an explicit persisted value is now authoritative in both directions, letting the toggle-off survive a restart. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
github-actions[bot]andmudler
|
0ae84be362 |
chore: bump inference defaults from unsloth (#10741)
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
97175f4b5a |
feat(model): debounce model loads after a failure to stop retry-storms (#10728)
A client that keeps polling a model whose load fails (e.g. a backend that crashes deterministically on init) triggered a fresh backend start on every request: request -> load -> crash in ~10s -> 500, repeat on the next poll. Each attempt could leak GPU/CUDA state, and under LOCALAI_SINGLE_ACTIVE_BACKEND it kept stealing the active slot from healthy models. The existing loading-coalesce map only dedups *concurrent* loads, so sequential polls were never covered. Track load failures per modelID in ModelLoader. After a load fails, refuse fresh load triggers for that model until a cooldown elapses, returning a typed ModelLoadCooldownError that the HTTP layer maps to 503 with a Retry-After header. The cooldown grows exponentially per consecutive failure (base, doubling, capped at 5m) and resets on a successful load. The coalesced follower-retry of an in-flight burst bypasses the gate, so a genuinely concurrent burst still gets its one retry -- only new, independent triggers are refused, matching the report's "refuse new load-triggers" wording. Configurable via --model-load-failure-cooldown / LOCALAI_MODEL_LOAD_FAILURE_COOLDOWN (default 10s, 0 disables), plumbed through ApplicationConfig and applied unconditionally at startup. Closes #10719 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
85f5267ed2 |
fix(llama-cpp): cap single-pass embedding batch to fit VRAM (#10695)
* fix(llama-cpp): cap single-pass embedding batch to fit VRAM Embedding/score/rerank all decode or pool the whole input in one physical batch, so EffectiveBatchSize sized the batch to the full context window. For a large context that makes n_ubatch huge, and the per-device CUDA compute buffer (forward-graph scratch, ~n_ubatch * n_ctx, NOT split across GPUs) balloons into multi-GiB: a large-context embedding model then aborts on load (exitCode=-1) even with plenty of free VRAM. Reproduced with qwen3-embedding-4b (context 40960 -> n_batch 40960 -> abort) and qwen3-embedding-0.6b (n_batch 8192); pinning batch:512 avoided it. This is the same root cause as issue #10485 (a large context turns the batch into multi-GiB of scratch that must fit on a SINGLE card), but the single-pass path bypassed the VRAM headroom guard the config layer already had — it returned the unbounded context as the batch with no GPU awareness. Make the single-pass batch VRAM-aware: cap it to the largest batch whose compute buffer fits the per-device VRAM headroom, clamped to [DefaultPhysicalBatch, ctx], reusing the existing computeBufferBytesPerCell and headroom-divisor math (no duplication). Unknown per-device VRAM (0) stays conservative (DefaultPhysicalBatch, not the context) so a detection gap can't OOM. The GPU is resolved through an injectable package var (config.LocalGPU, backed by sync.Once-cached xsysinfo detection) so the per-request router call stays cheap and tests inject a deterministic device. Explicit batch: still wins. An input longer than the cap can no longer be pooled in one pass — the accepted tradeoff, since a batch that OOMs the device processes nothing. Assisted-by: Claude:claude-opus-4-8 golangci-lint go-test Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(config): single-pass batch follows context on unknown VRAM The single-pass (embedding/score/rerank) batch cap must only shrink the batch when the per-device VRAM ceiling is KNOWN. On unknown VRAM (CPU-only or a GPU detection gap) SinglePassBatchForContext returned DefaultPhysicalBatch, which under-sized the batch below the context — over-trimming score/embed/rerank inputs (the modelTokenTrim middleware regression) with no OOM benefit on CPU where the compute buffer lives in system RAM. Return the full context instead, preserving the original single-pass behavior; the VRAM cap stays a downward safety that only engages when VRAM is known. Assisted-by: Claude:claude-opus-4-8 [go-test go-vet] 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
ed3b59baf1 |
fix(config): cap auto-derived context to fit VRAM (#10696)
When a model is imported without an explicit context_size, the GGUF importer defaulted the model's context to its full trained window (n_ctx_train). For long-context models (128k / 256k / 1M) that KV cache cannot fit a consumer GPU, so the backend aborts on load (exitCode=-1) even though the model file is perfectly fine. Reproduced live: gemma-4-26b-a4b-it-qat-q4_0 defaulted to context=262144 and qwythos-9b-claude-mythos-5-1m to 1048576, both aborting on a 20 GB card. Instead of chasing the trained max, auto-derive a conservative default: min(trainedMax, DefaultAutoContextSize=8192). A small model keeps its trained window; a long-context model caps at 8k and users opt into more via context_size. This cap applies always, including CPU / unknown-VRAM hosts, so it never regresses those paths. Per-device VRAM is used only as a DOWNWARD safety: when a per-device ceiling is detected (xsysinfo.MinPerGPUVRAM) and even the 8k cap would not fit it with headroom, step down through candidate contexts to the largest that fits, floored at DefaultContextSize. When VRAM is unknown (0) or no GPU is detected we do NOT clamp — the bug is GPU OOM and the 8k cap is already safe, so detection gaps must not shrink the window. The footprint estimate reuses gpustack/gguf-parser-go's EstimateLLaMACppRun at a given context with all layers offloaded, taking the per-device NonUMA VRAM figure. The estimate and VRAM detection are package vars so tests inject deterministic values. Explicit context_size always wins (guessGGUFFromFile only acts when it is nil). Assisted-by: Claude:claude-opus-4-8 [golangci-lint go-test] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
b0959d4756 |
feat(api): add GET /v1/models/capabilities endpoint (#10687)
Additive superset of /v1/models that enriches each model entry with the capabilities it supports plus its input/output modalities (text / image / audio / video). Clients that only understand /v1/models are unaffected -- they simply never call the new route. Audio and video *input* are derived from the model's multimodal limits (vLLM limit_mm_per_prompt), which no single usecase FLAG expresses. That gap is exactly why a plain capability list is insufficient and this enriched endpoint exists: an attachment router can now decide whether an image/audio/video file can go to the active model directly, or must be converted/transcribed first. Capability derivation lives in core/config as the single source of truth (ModelConfig.Capabilities / InputModalities / OutputModalities / VisionSupported / ...); the Ollama capability surface now delegates to it instead of keeping a parallel copy. Vision is gated on chat/completion capability so a MediaMarker hydrated onto a non-chat model (e.g. a pure ASR/TTS backend) no longer reports a false vision capability. Read-only listing: no new FLAG_* flag, reuses the existing `models` swagger tag, and intentionally exposes no MCP admin tool (there is nothing to manage conversationally). 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> |
||
|
Ettore Di Giacinto
|
1152acc167 |
Revert "feat(config): default swa_full:true for sliding-window-attention models" (#10674)
Revert "feat(config): default swa_full:true for sliding-window-attention mode…"
This reverts commit
|
||
|
Richard Palethorpe
|
eb32cd9073 |
feat(realtime): eager blocking pipeline warm-up + /backend/load API (#10662)
Realtime sessions previously lazy-loaded each pipeline sub-model (VAD,
transcription, LLM, TTS) on first use, so every cold session paid a
per-request model-load stall and load errors only surfaced mid-stream.
Warm the whole pipeline eagerly and blockingly at session start
(including the voice-gate speaker-recognition model, which an enforced
gate blocks each utterance on; compaction's summary_model stays lazy
since it only runs off the response path):
- Add backend.PreloadModel / PreloadModelByName as the single load path
for every modality (no transcription special-case; backend-omitted
configs are deprecated).
- The realtime session blocks on Model.Warmup and returns a
model_load_error to the client if any stage fails to load;
updateSession warms in the background. Opt out per pipeline with
pipeline.disable_warmup, exposed as a UI toggle via the
config-metadata registry.
Add a LocalAI-native POST /backend/load (and /v1/backend/load) that
pre-loads a model -- expanding realtime pipelines into their sub-models
-- as the inverse of /backend/shutdown. There is one preload engine
(backend.PreloadStages): the realtime Warmup methods, /backend/load and
the --load-to-memory startup flag all use it, so --load-to-memory now
also expands pipeline models and records load-failure traces. Pipeline
sub-model alias resolution is likewise shared
(ModelConfigLoader.LoadResolvedModelConfig). Surface the endpoint
everywhere an admin manages models:
- MCP admin tool load_model (httpapi + inproc clients, safety/catalog
prompts, catalog/dispatch tests).
- "Load into memory" action in the React models UI.
- Swagger regenerated; docs moved to the general backend-monitor page
since it is not realtime-specific.
Fix a Traces UI crash ("json: unsupported value: -Inf"): audio-snippet
RMS/peak now floor at a finite dBFS, and backend-trace data is sanitized
to drop non-finite floats before marshaling. The sanitizer is
copy-on-write -- it runs on every RecordBackendTrace, so containers are
only re-allocated on the paths that actually changed.
Migrate core/http/openresponses_test.go onto the prebuilt mock-backend
the rest of the http suite already uses -- it was the last spec still
pointing at a real HuggingFace model, so it 404'd wherever no vision
backend was built -- and fix its item_reference specs to send the
spec's "id" field instead of "item_id", which the handler never
accepted.
Assisted-by: Claude:claude-opus-4-8 Claude Code
Signed-off-by: Richard Palethorpe <io@richiejp.com>
|
||
|
LocalAI [bot]andEttore Di Giacinto
|
02b007a31e |
feat(config): default swa_full:true for sliding-window-attention models (#10611)
LocalAI enables a cross-request prompt-prefix cache (cache_reuse, see core/config/serving_defaults.go) so repeated prefixes — system prompts, RAG context, agent scaffolds, multi-turn chat — are not reprocessed every turn. For sliding-window-attention (SWA) models (Gemma 2/3, Cohere2, Llama 4, ...) this silently does nothing: llama.cpp defaults to a reduced SWA KV cache sized to the sliding window, and that reduced cache cannot preserve a prompt prefix across requests, so every turn reprocesses the whole prompt anyway. llama.cpp's --swa-full (params.swa_full, already wired through the LocalAI llama.cpp backend's `swa_full` option) keeps the full KV cache so the shared prefix is reused. Enable it automatically, but only for models that are actually SWA: detection reads the gguf-parser-normalized `<arch>.attention.sliding_window` metadata (which also applies llama.cpp's family rules, e.g. Phi-3 → not SWA), right where the GGUF is already parsed for defaults. It is never applied to dense models (pure memory waste) and never overrides an explicit user `swa_full`/`n_swa` choice. Tradeoff: the full SWA cache scales with context_size, so it costs more memory at large contexts — hence the SWA gating and the documented `swa_full:false` opt-out. Assisted-by: Claude:claude-opus-4-8 [Claude Code] golangci-lint Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
fd8cebd0b3 |
fix(watchdog): persist UI-saved Check Interval across restarts (#10601) (#10605)
fix(watchdog): persist a UI-saved Check Interval across restarts (#10601) The watchdog Check Interval saved via /api/settings reverted to 500ms on every restart, while the idle/busy timeouts persisted correctly. Root cause: NewApplicationConfig baseline-defaulted WatchDogInterval to 500ms, whereas the idle/busy timeouts default to 0. The startup loader (loadRuntimeSettingsFromFile) applies a persisted runtime_settings.json value only when the field is still at its zero default - its heuristic for "this wasn't set by an env var". Because the interval was always 500ms at that point, the loader never read the persisted value back, so the saved interval was silently discarded on each boot. Fix: drop the non-zero baseline default so the interval behaves like the sibling timeouts (0 = unset). The effective 500ms default is now supplied at the watchdog layer: WithWatchdogInterval ignores a non-positive value so DefaultWatchDogOptions' 500ms is preserved (and a 0 interval can never turn the watchdog loop into a busy spin). Also mirror the interval in the live config file watcher alongside idle/busy, and report the real 500ms default (not the stale "2s") from ToRuntimeSettings. 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
|
5d0c43ec6e |
feat(realtime): Semantic VAD EOU token (#10444)
* feat(realtime): EOU-driven semantic_vad turn detection Add a `semantic_vad` turn-detection mode to the realtime API that feeds the transcription model live and decides "the user finished speaking" from the `<EOU>` end-of-utterance token rather than from silence alone. When EOU fires the turn commits immediately (~0.3s); otherwise it falls back to an eagerness-scaled silence threshold (low/med/high = 8/4/2s). Plumbing, bottom to top: - proto: `AudioTranscriptionLive` bidirectional RPC (config-first oneof, mono float PCM @16k, ready-ack / Unimplemented degrade signal) plus `TranscriptResult.eou` for the unary retranscribe gate. - pkg/grpc: client/server/base/embed scaffolding for the bidi stream, modeled on AudioTransformStream; release stream conns on terminal Recv. - parakeet-cpp: live transcription RPC with per-C-call engine locking (one live stream per turn, finalize+free at commit); bump parakeet.cpp to ABI v5 — incremental StreamingMel (no more quadratic per-feed mel recompute that delayed EOU on long turns) and the <EOU>/<EOB> split; strip the literal <EOU>/<EOB> from offline text and set Eou. - core/backend: LiveTranscriptionSession wrapper + pipeline `turn_detection:` config block (type/eagerness/retranscribe). - realtime: semantic_vad integration — live input captions streamed as transcription deltas while the user speaks, EOU-immediate commit with eagerness fallback, optional retranscribe gate (batch re-decode must also end in <EOU> to confirm), clause synthesis off the LLM token callback, and per-turn live-transcription / model_load telemetry. - UI: show the realtime pipeline components as a vertical list. Docs and tests included; opt-in via the pipeline YAML or per-session `session.update`. Non-streaming STT backends degrade to silence-only. Assisted-by: Claude Code:claude-opus-4-8 [Read] [Edit] [Write] [Bash] Assisted-by: Claude Code:claude-fable-5 [Read] [Edit] [Bash] Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat(realtime): explicit formally-verified state machines + parakeet streaming driver The realtime API had several implicit state machines whose state was inferred from scattered booleans, channels, and five separate mutexes, leaving illegal/inconsistent states reachable. Make them explicit and keep the implementation in step with a formal design; rework the parakeet streaming backend along the same lines. Realtime state machines (M1-M5). Each is a sealed sum-type State/Event/Effect with a total, pure Next(state,event)->(state,[]effect) behind a single-writer Coordinator: M1 conncoord connection lifecycle: VAD toggle + once-only teardown (replaces vadServerStarted + a `done` channel closed from two sites). M2 turncoord turn detection: collapses speechStarted and the live-stream "turn open" flag into one state, so discardTurn can no longer desync them and suppress the next onset. M3 respcoord response coordination: serializes the dual-writer start/cancel so at most one response is live; one response.done per response.create. M4 compactcoord conversation compaction: single-flight (replaces the `compacting atomic.Bool` CAS). M5 ttscoord TTS pipeline: open->closing->closed, idempotent wait(), rejects enqueue-after-close (was a silent drop). The Coordinator/Sink/Next plumbing — only the sealed types and Next differed per machine — is extracted once into core/http/endpoints/openai/coordinator as a generic Coordinator[S,E,F]; each machine keeps its public API via type aliases, so no sink, call-site, or test moved. Hierarchy. session_lifecycle.fizz models M1 as the parent region with its children (M2/M3/M4) as one statechart and asserts ChildrenDieWithParent (conn torn => all children terminal, none start after teardown). respcoord and compactcoord gain an absorbing Terminated state + Shutdown event; conncoord's teardown drives the children terminal. This closes a compaction teardown gap: a fire-and-forget compaction could outlive a torn session — compactionSink now takes a session-scoped cancellable context + WaitGroup and joins the in-flight summarize+evict on shutdown. Formal verification. formal-verification/ holds one authoritative FizzBee spec per machine plus the composition spec, each with an always-assertion and a documented one-line edit that makes the checker fail (verified non-vacuous). scripts/realtime-conformance.sh is fail-closed: all Go conformance suites under -race AND a model-check of every .fizz spec; a missing FizzBee is a hard error (only the loud REALTIME_CONFORMANCE_SKIP_FIZZBEE=1 bypasses it, never in CI). FizzBee is pinned by sha256 and installed via scripts/install-fizzbee.sh into .tools/ (gitignored). Wired as make test-realtime-conformance, a CI workflow, and a pre-commit path filter. Go conformance tests are Ginkgo/Gomega (per the repo's forbidigo lint): transition tables + fixed-seed property walks + concurrent/-race specs, no rapid dependency. Design map: docs/design/realtime-state-machines.md. Parakeet streaming backend. The same treatment applied to the parakeet-cpp streaming paths: - AudioTranscriptionStream returns codes.Unimplemented for non-streaming models instead of decoding offline and emitting it as one delta + final. A client that asked for streaming learns the model cannot stream rather than receiving a batch result shaped like a stream. New grpcerrors.StreamTranscriptionUnsupported carries that signal; the HTTP /v1/audio/transcriptions stream path surfaces it as an SSE error event. Mirrors AudioTranscriptionLive, which already did this. - utteranceBoundary (boundary.go): a single definition of the end-of-utterance latch, replacing three open-coded finalEou toggles. Modelled as a two-valued type so illegal states are unrepresentable. - Shared decode driver (driver.go): streamFeedResult (one per-feed event) + feedChunk (hides the ABI v4 JSON vs text-only split) + feedSlices + flushTail. The feed loop is written once. - AudioTranscriptionLive becomes a bidi adapter: it streams the per-feed {delta,eou,eob,words} the realtime turn detector consumes and a terminal FinalResult carrying only Text. Segments/duration/eou are offline-only and no longer produced (nor read) on the live path; liveTraceState drops the terminal eou and keeps the per-feed eou_events count. - AudioTranscriptionStream + streamJSON merge into one driver-based function; streamSegmenter is generalized to the unified event with a text-only fallback that preserves the legacy (no-words) library's per-utterance segmentation. Verified: build/vet/gofumpt clean, golangci-lint 0 issues, all coordinator and parakeet packages under -race, the fail-closed conformance gate green, and make test-realtime (12 e2e WS+WebRTC). Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
de2ec2f136 |
feat(backends): add voice-detect + face-detect ggml backends (replace Python insightface/speaker-recognition) (#10441)
* feat(voice-detect): add Go purego backend for voice-detect.cpp Add backend/go/voice-detect implementing the Backend gRPC voice subset (VoiceEmbed/VoiceVerify/VoiceAnalyze) over libvoicedetect.so via purego, mirroring the parakeet-cpp / omnivoice-cpp backends. The flat voicedetect_capi C ABI is dlopen'd cgo-less; malloc'd string and float-vector returns are owned by Go and released through the matching capi free functions, with the per-ctx last error surfaced into Go errors. Calls are serialized via base.SingleThread since the C context is not reentrant. Proto field mapping: - VoiceEmbed: VoiceEmbedRequest.audio (path) -> embed_path -> Embedding+Model. - VoiceVerify: audio1/audio2 + threshold (<=0 falls back to the verify_threshold option, default 0.25) -> verify_paths -> verified/distance/ threshold/confidence/model/processing_time_ms. - VoiceAnalyze: audio (path) -> analyze_path_json; the JSON age/gender/emotion document maps to a single VoiceAnalysis segment (start/end 0; gender "label" -> dominant_gender with the remaining float scores as the gender map; emotion label/scores -> dominant_emotion/emotion). The Makefile pins voice-detect.cpp to 47546430, clones+builds libvoicedetect.so with ggml static-linked (PIC, GGML_NATIVE off) so dlopen needs no external libggml/libvoicedetect; ldd on the artifact shows only system libs. Ginkgo tests cover option parsing and analyze-JSON mapping; embed/verify smoke specs gate on VOICEDETECT_BACKEND_TEST_MODEL + VOICEDETECT_BACKEND_TEST_WAV. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(voice-detect): wire backend into index, gallery and build Register the voice-detect.cpp speaker-recognition + voice-analysis backend (added in Voice-INT-A) into LocalAI's distribution surfaces, mirroring the ced backend (the closest mudler C++/ggml audio analogue): - backend/index.yaml: add the &voicedetect meta-backend (capabilities platform map, no top-level uri) plus the full set of concrete per-arch image entries (cpu/cuda12/cuda13/metal/rocm/sycl/vulkan/l4t and the -development variants). Referential integrity audited - every alias target resolves. - gallery/index.yaml: add 5 model entries on backend voice-detect - ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++ and the wav2vec2 age/gender/emotion analyze model. The engine architecture is read from GGUF metadata (voicedetect.arch) at load. GGUF artifacts are not yet published: each files: entry points at the intended mudler/voice-detect-gguf location with a TODO to fill sha256 after upload (no fabricated hashes). - .github/backend-matrix.yml: add the linux build matrix block + the darwin metal entry mirroring ced. - .github/workflows/bump_deps.yaml: track mudler/voice-detect.cpp via VOICEDETECT_VERSION (pin 47546430, = 4754643). - core/config/backend_capabilities.go: register voice-detect in the backend capability map (VoiceVerify/VoiceEmbed/VoiceAnalyze -> speaker_recognition), mirroring speaker-recognition. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(face-detect): add purego Go backend for face-detect.cpp Add the LocalAI Go backend that dlopens libfacedetect.so (the flat facedetect_capi_* C-ABI) via purego, mirroring the sibling voice-detect backend. Implements the Face subset of the Backend gRPC service: - Embeddings(PredictOptions): Images[0] base64 -> temp file -> embed_path -> L2-normalized ArcFace embedding. - Detect(DetectOptions): src -> detect_path_json -> Detection boxes (class_name "face", [x1,y1,x2,y2] -> x/y/w/h). - FaceVerify(FaceVerifyRequest): two images + threshold + anti_spoof -> verify_paths; best-effort img areas via detect. - FaceAnalyze(FaceAnalyzeRequest): img -> analyze_path_json -> per-face age + gender ("M"/"F" normalized to "Man"/"Woman"). The Makefile pins face-detect.cpp to 636a1963 and builds the shared lib with ggml + vendored libjpeg-turbo static (PIC), so the .so is ldd-clean (no libggml) and exports only facedetect_capi_* (no jpeg_ symbols). Gated Ginkgo e2e mirrors voice-detect. Note for the gallery-wiring task: backend registration (index.yaml, gallery, core/config/backend_capabilities.go) is intentionally not touched here. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * fix(voice-detect): replace em dashes in net-new descriptions Project style forbids em/en dashes. Replace the three U+2014 chars introduced by the voice-detect gallery/index wiring with `-`/`:`. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(face-detect): wire backend into index, gallery and build Register the face-detect.cpp face detection / embedding / verification / analysis backend (added in Face-INT-A) into LocalAI's distribution surfaces, mirroring the voice-detect wiring (the closest mudler C++/ggml recognition analogue): - backend/index.yaml: add the &facedetect meta-backend (capabilities platform map, no top-level uri to avoid the meta-backend gotcha) plus the full set of concrete per-arch image entries (cpu/cuda12/cuda13/ metal/rocm/sycl-f16/sycl-f32/vulkan/l4t and the -development variants), 22 entries. Referential integrity audited: every alias target resolves. - gallery/index.yaml: add 4 model entries on backend face-detect - face-detect-buffalo-l/m/s (insightface SCRFD + ArcFace/MBF, NON-COMMERCIAL) and face-detect-yunet-sface (OpenCV-Zoo YuNet + SFace, APACHE-2.0, the commercial-friendly alternative). The detector/embedder architecture is read from GGUF metadata (facedetect.arch) at load; only the real verify_threshold option is set (0.35 buffalo, 0.363 sface). GGUF artifacts are not yet published: each files: entry points at the intended mudler/face-detect-gguf location with a TODO to fill sha256 after upload (no fabricated hashes). - core/config/backend_capabilities.go: register face-detect in the backend capability map (Embedding/Detect/FaceVerify/FaceAnalyze -> face_recognition), mirroring insightface. - .github/backend-matrix.yml: add the linux build matrix block + the darwin metal entry mirroring voice-detect. - .github/workflows/bump_deps.yaml: track mudler/face-detect.cpp via FACEDETECT_VERSION (pin 636a1963). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * fix(recon): voice-detect metal build branch + face-detect gallery usecases Add the missing metal BUILD_TYPE branch to the voice-detect Makefile forwarding -DVOICEDETECT_GGML_METAL=ON, mirroring face-detect, so the darwin metal CI artifact is built with the Metal backend instead of CPU-only. Expand the 4 face-detect gallery models' known_usecases to [face_recognition, detection, embeddings] to match the backend capabilities map and the mirrored insightface-buffalo entries, so auto-selection for /v1/detect and /embeddings works. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * docs(recon): document voice-detect and face-detect ggml backends Document the new standalone C++/ggml biometric backends as the recommended/default option for face and voice recognition, keeping the existing Python insightface / speaker-recognition backends framed as the legacy path. - features/face-recognition.md: add a face-detect (ggml) backend section with the gallery entries (buffalo-l/m/s non-commercial, yunet-sface Apache-2.0), licensing, and verify/detect/analyze quickstart. - features/voice-recognition.md: add a voice-detect (ggml) backend section with the gallery entries (ecapa-tdnn, wespeaker-resnet34, eres2net, campplus speaker recognizers; emotion-wav2vec2 non-commercial analyze head) and quickstart. - reference/compatibility-table.md: add face-detect.cpp and voice-detect.cpp rows to the Vision, Detection & Recognition table. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(gallery): publish recon backend GGUF uris + sha256 Fill in the published HuggingFace GGUF uris and verified sha256 for the 9 recon gallery entries (voice-detect-* and face-detect-*), and remove the TODO publish markers. Correct the eres2net, campplus, and emotion-wav2vec2 uris to the actual published filenames. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(gallery): re-embed buffalo anti-spoof + add audeering age/gender voice model Update the 3 buffalo face-detect GGUF sha256 (anti-spoof ensemble now embedded and re-uploaded under the same filenames/uris) and note the FaceVerify anti_spoof request flag in each description. Add a new voice-detect-age-gender-wav2vec2 gallery entry mirroring the emotion model. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(gallery): add face-detect-buffalo-sc and antelopev2 packs Add gallery entries for two newly-published insightface face packs on the face-detect backend: buffalo_sc (smallest pack, SCRFD-500M + small ArcFace) and antelopev2 (higher-accuracy, SCRFD-10G + ArcFace glint360k R100, 512-d). Both are non-commercial research-only. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(recon): honor LocalAI per-model threads in voice/face-detect backends LocalAI spawns one backend process per model and serves requests concurrently, so the engines' own min(hardware_concurrency, 8) default can oversubscribe cores. Forward the per-model Threads value from the gRPC LoadModel options into the engine via VOICEDETECT_THREADS / FACEDETECT_THREADS (read at backend construction) before the capi load. A non-positive Threads is treated as unset, leaving the engine default. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump backend pins to CPU-optimized engine commits voice-detect.cpp -> 0d9c1b3 (radix-2 FFT FBank, threads, flash attn + cached pos-conv); face-detect.cpp -> 523aee1 (thread-gated direct conv, threads). Brings the CPU optimizations into the LocalAI backend builds. GGUF format and parity unchanged, so the published HF GGUFs remain valid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump backend pins to round-2 CPU-optimized engines voice-detect.cpp -> fe7e6a3 (ERes2Net 1x1->mul_mat, CAM++ layout+context, wav2vec2 conv-LN, ECAPA capture-drop, AVX512 dispatch opt-in); face-detect.cpp -> 9c8adb7 (AVX2 Winograd F(2x2,3x3) for SCRFD/ArcFace 3x3 convs, ArcFace BN-fold). Parity unchanged (cosine=1.0); GGUF format unchanged, HF GGUFs valid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump backend pins to round-3 Winograd engines voice-detect.cpp -> 45122ec (Winograd F(2x2,3x3) for WeSpeaker/ERes2Net 3x3 convs, -22%/-20% @8t); face-detect.cpp -> cd5c962 (Winograd F(4x4,3x3) for SCRFD large maps, -22% @1t on top of F(2x2), more load-stable). Parity held (cosine=1.0); GGUF format unchanged, HF GGUFs valid. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump backend pins to round-4 Winograd engines (CPU opt complete) voice-detect.cpp -> d2839ca (CAM++ FCM 2D convs through Winograd, -15.5%/-10.3%); face-detect.cpp -> c1db23d (AVX2-vectorized Winograd tile transforms, SCRFD detect -14%/-9.6%). Final CPU optimization round; the conv-kernel lever class is now exhausted (parity held cosine=1.0; GGUF/parity unchanged, HF GGUFs valid). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump face-detect pin to deep-kernel engine (7ae5c4d) face-detect.cpp -> 7ae5c4d: register-blocked winograd-domain GEMM microkernel (2.8x isolated GFLOP/s), AVX-512 zmm evolution behind runtime CPUID dispatch (ship-safe, AVX2 fallback bit-identical), bias/relu fused into the winograd output transform, and SFace Conv+BN fold + bias/PReLU fusion. SCRFD detect ~1.4x faster end-to-end vs the round-4 baseline; parity bit-exact; portable single binary (function-multiversioned, no global -mavx512f). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump voice-detect pin to ECAPA operand-order win (e9c56ae) voice-detect.cpp -> e9c56ae: weight-as-src0 mul_mat order in ECAPA's F32 conv1d_same (routes through tinyBLAS sgemm); ECAPA embed 1.67x @1t / ~1.3x @8t, parity cosine=1.0. Isolated to encoder.cpp (ECAPA-only); ERes2Net/CAM++/WeSpeaker do not call conv1d_same so are provably unaffected. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump pins to FMA-throughput engines (voice f7b9f89, face 2d2d5f0) face -> 2d2d5f0: route ArcFace 3x3 body convs through the AVX-512 winograd microkernel (kWinoMinSize 80->14); ArcFace 1.62x @1t, SCRFD detect to 0.966 of MLAS @1t, no regression. voice -> f7b9f89: runtime-CPUID-dispatched AVX-512 winograd-GEMM microkernel (ship-safe, AVX2 fallback bit-identical); WeSpeaker 1.90x @1t. Parity cosine=1.0 throughout; portable single binaries. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump pins to MLAS-class direct-conv engines (voice 7ecfd07, face be22d67) Hand-tuned nChw16c AVX-512 register-tiled direct-conv microkernel (~263 GFLOP/s, within 6-7% of MLAS per-op efficiency), runtime-CPUID-dispatched + AVX2 fallback, fused bias/relu. voice 7ecfd07: default 3x3-s1 kernel for WeSpeaker (+37%/+32%) + ERes2Net, CAM++ pinned to Winograd. face be22d67: shape-gated to the ArcFace recognizer body (+25-27% @8t); SCRFD detector stays on Winograd (no regression). Parity cosine=1.0 / detect <=1px on AVX-512 + AVX2 paths. Portable single binaries. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump voice pin to Phase-A blocked backbone (f4e7eef) WeSpeaker ResNet34 runs as one nChw16c blocked island (2 reorders/forward vs ~60) on AVX-512, default; per-conv directconv fallback on AVX2. +2.9% @1t / +17-19% @8t vs per-conv directconv, parity cosine=1.0. The conv microkernel is already FMA-bound near peak (~0.86-0.98x MLAS-implied); residual to MLAS is sub-peak edge + non-conv tail, documented in docs/cpu-optimization.md. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump pins to breadth blocked-backbone (voice 7f66871, face d80092b) voice 7f66871: AVX2-vectorized (ymm) blocked island - AVX2-only hosts now run the blocked backbone for WeSpeaker (2.3x over per-conv-AVX2, cosine=1.0); ERes2Net stays per-conv (blocked regresses, opt-in only); CAM++ Winograd-pinned. face d80092b: ArcFace recognizer blocked island, AVX-512 default (-13% @8t, ~0.90x MLAS, the closest conv result), auto per-conv on AVX2; SCRFD untouched on Winograd (0 island invocations during detect). Parity cosine=1.0 / detect <=1px throughout. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump pins to small-spatial + stem conv kernels (voice 99b1804, face 47fdab6) Measured-gap-driven conv kernels: small-spatial (fill the register tile when output width <= tile width) + small-IC stem + strided-1x1/downsample recovery. ArcFace recognizer 0.57 -> 0.70x MLAS @1t (the closest conv model), WeSpeaker 0.65 -> 0.79x @1t. Parity cosine=1.0 / detect <=1px. The OC-block-sharing lever was a measured dead-end (deep stride-1 is L3-weight-bandwidth bound, not read-port bound) and was NOT shipped. Kernel ceiling reached; further gap needs an algorithm-class change (cache-blocked weight-stationary GEMM, or q8 weights). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump pins to GPU persistent-graph + multi-model-safe cache (voice 45d2e6b, face 0a4799a) GPU wins (CUDA/ggml backend, no CPU-path change): persistent per-shape graph+context cache in Backend::compute() eliminates the per-call cudaGraph re-instantiation churn -> wav2vec2 emotion+age-gender now AT GPU parity with torch-cuDNN on GB10 (0.97-0.98x), CAM++ -5.7ms; bit-identical parity. Cache hardened multi-model-safe (invalidate-on-free keyed by the ModelLoader weights buffer) so LocalAI multi-model hosting cannot stale-hit. Conv models still trail cuDNN (im2col-materialization-bound) - cuDNN implicit-GEMM lever next. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump pins to cuDNN-conv-capable engines (voice b6e4356, face 6107a24) Adds the opt-in cuDNN implicit-GEMM conv path (VOICEDETECT_GGML_CUDNN / FACEDETECT_GGML_CUDNN, DEFAULT OFF -> zero build/runtime dep until enabled). On GPU it kills the im2col-materialization bottleneck and reaches torch-cuDNN parity on the spill-bound convs: SCRFD detect 14.8->6.4ms (2.3x, ~parity), WeSpeaker ~parity, ERes2Net beats torch (1.10x); ArcFace/CAM++ neutral (no spill). Parity exact (SCRFD <=1px, cosine=1.0). To USE it in LocalAI, the CUDA backend build must enable the flag AND bundle libcudnn - deferred until a cuDNN-bundled GPU image; flag stays OFF here. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * feat(recon): enable cuDNN conv path on arm64+CUDA13 recon backends The voice-detect.cpp / face-detect.cpp engines have an opt-in cuDNN implicit-GEMM conv path behind VOICEDETECT_GGML_CUDNN / FACEDETECT_GGML_CUDNN (default OFF) that kills im2col on the GPU and reaches torch-cuDNN parity (SCRFD 2.3x, WeSpeaker/ERes2Net parity), measured on the GB10 (arm64, CUDA 13, sm_121a). Enable it for the CUDA build, but only where cuDNN actually ships: the arm64 + CUDA 13 image (GB10/Jetson/L4T). x86 CUDA images carry no cuDNN, so flipping it on globally for BUILD_TYPE=cublas would be a link failure. The Makefiles gate on CUDA_MAJOR_VERSION=13 + arch (TARGETARCH from the matrix/Docker build, uname -m fallback for local builds). backend/Dockerfile.golang already installs the runtime libcudnn9-cuda-13 in the arm64+CUDA13 apt block; add the matching libcudnn9-dev-cuda-13 so the build-time link resolves. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): bump voice-detect pin to ERes2Net blocked-default (30beecd) Defaults VD_ERES2NET_BLOCKED ON: routes the ERes2Net Res2Net body through the blocked nChw16c AVX-512 directconv island instead of the 1x1 mul_mat fast path (CONT-transpose + skinny low-K GEMM). On the shipped GGML_NATIVE=OFF build (ggml mul_mat is AVX2-only) this wins ~2x at every thread count (2.07x@1t, 2.2x@4t, 2.05x@8t); pure-AVX2 fallback still 1.3-1.62x. Parity exact (cosine=1.000000 vs golden), so registered voices + verify/identify thresholds are unaffected. The prior default-OFF rested on a stale comment whose 23pct regression only held on the non-shipping GGML_NATIVE=ON build. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * docs(readme): announce native voice-detect + face-detect backends in Latest News Add a Latest News entry for the new from-scratch C++/ggml biometric backends (voice-detect.cpp + face-detect.cpp) that replace the Python insightface and speaker-recognition backends: no Python/onnxruntime at inference, self-contained GGUF, bit-exact parity, GPU cuDNN parity. Mirrors the parakeet.cpp / locate-anything.cpp native-backend news entries. Refs PR #10441. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * chore(recon): re-pin to the squashed engine release commits The voice-detect.cpp and face-detect.cpp histories were squashed to a single release commit, which orphaned the previous pins (voice 30beecd, face 6107a24). Re-pin to the new single-commit SHAs (voice 3d51077, face 06914b0); the tree is identical, so the backend build is unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
f3d829e2ef |
feat(distributed): add LOCALAI_DISTRIBUTED_SHARED_MODELS to skip staging on shared volumes (#10556) (#10566)
In distributed mode, even when the frontend and workers share the same models directory via a shared volume mount, starting a model on a worker re-staged (re-downloaded) it: stageModelFiles always uploads model files into a tracking-key-namespaced subdir on the worker, and the staging probe only checks that staged location, so a file already present on the shared volume at the canonical path was never reused. Add a config switch LOCALAI_DISTRIBUTED_SHARED_MODELS (default false). When enabled, the operator asserts that all nodes mount the SAME models directory at the SAME path, so staging is unnecessary: the frontend's absolute model paths are already valid on the worker. In that mode stageModelFiles returns the cloned opts unchanged without uploading, leaving the path fields pointing at their canonical absolute paths so the worker loads them directly from the shared volume. The value is plumbed from DistributedConfig through SmartRouterOptions into the SmartRouter. Docs and docker-compose.distributed.yaml updated. 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
1154be5eea |
fix(config): fall back to DefaultContextSize for unparseable GGUFs; pin NVFP4 gallery context_size (#10563)
The GGUF metadata parser (gpustack/gguf-parser-go) cannot read NVFP4-quantized GGUFs at all: it errors with "read tensor info 0: This quantized type is currently unsupported" because NVFP4 is a ggml tensor type it does not know. When ParseGGUFFile errors, the llama-cpp defaults hook skips guessGGUFFromFile entirely and the deferred fallback sets the context window to the conservative GGUFFallbackContextSize (1024). The result: a model that trains to 262144 tokens runs with n_ctx=1024, and every prompt over ~1k tokens fails with "request (N tokens) exceeds the available context size (1024 tokens)". Two changes: - Drop GGUFFallbackContextSize (1024) and fall back to DefaultContextSize (4096) in both the GGUF run-estimate path (gguf.go) and the deferred hook fallback (hooks_llamacpp.go). 1024 is a sensible floor for a tiny CPU GGUF but a footgun for a large, long-context model whose header simply cannot be parsed. Strengthen the existing "GGUF unreadable" test to assert the value. - Set context_size explicitly on the four NVFP4 gallery entries (qwen3.6-35b-a3b-nvfp4-mtp, qwopus3.6-27b-v2-mtp-nvfp4, qwopus3.6-27b-coder-mtp-nvfp4, qwen3.6-27b-nvfp4-mtp) so the parser failure is irrelevant for them. 32768 matches sibling Qwen entries and is safe on memory; operators can raise it toward the 262144 train length. 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
79783120dd |
fix(config): gate parallel-slot default on per-device VRAM too (#10485) (#10507)
The first #10485 fix (#10494) made the Blackwell physical-batch boost per-device/context-aware, which neutralized the big compute-buffer OOM, but the reporter's 2x16 GiB consumer Blackwell still OOM'd. Tracing the post-fix log: the model now loads its weights, builds the main context and warms up fine, and dies only on the *last* allocation — the MTP draft context's 800 MiB KV cache on the tighter device. #10411 changed only two defaults: the physical batch (now gated) and a VRAM-scaled parallel-slot count. The KV cache is unified (n_ctx_seq == full context proves slots share the budget, so parallel doesn't multiply KV), but n_seq_max=4 still adds per-slot compute-graph / context-checkpoint / output scratch. On a device packed ~99% by a 27B model spanning both cards, that overhead is the few-hundred-MiB straw — which is why reverting #10411 (and only #10411) restores a working load. Gate the parallel-slot default on the same per-device headroom predicate as the batch boost: when a large context already fills a single card (largeContextForDevice), keep n_parallel=1. A user running one big-context model that barely fits across two consumer GPUs is not serving four concurrent tenants. Small contexts and large unified-memory devices (GB10) keep full concurrency. Applied on both the single-host path and the distributed router. Also make the auto-tuning visible and reversible (the debugging here needed DEBUG logs and a git bisect): - Log the effective performance-relevant runtime options at INFO once per model load ("effective runtime tuning …": context, n_batch, n_gpu_layers, parallel, flash_attention, f16) so an admin can see what will run and pin or override any value in the model YAML. - LOCALAI_DISABLE_HARDWARE_DEFAULTS=true skips the hardware auto-tuning entirely (mirrors LOCALAI_DISABLE_GUESSING) for stock llama.cpp behavior. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
fe4f425fb5 |
fix: correct scheme/host on self-referential URLs behind an HTTPS reverse proxy (#10482) (#10504)
* fix(http): harden BaseURL proxy scheme/host detection Split comma-separated X-Forwarded-Proto and honor the RFC 7239 Forwarded header so generated links use https behind common reverse-proxy setups. Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(http): honor explicit external base URL in BaseURL When _external_base_url is set in the request context it dictates the origin (scheme+host+port); the proxy path prefix is still appended. Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(config): generalize LOCALAI_BASE_URL to ExternalBaseURL LOCALAI_BASE_URL now sets a single instance-wide external base URL used for OAuth callbacks and all self-referential links. A Pre middleware stamps it into the request context for middleware.BaseURL. Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: document LOCALAI_BASE_URL and reverse-proxy headers Refs #10482 Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(http): cover parseForwarded edge cases; clarify base-url flag group Adds direct unit coverage for quoted/malformed/multi-element Forwarded headers and regroups the external base URL flag away from auth-only. Refs #10482 Assisted-by: Claude:claude-opus-4-8 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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
0d6de15ae9 |
fix(config): per-device VRAM headroom for Blackwell defaults (#10485) (#10494)
The hardware-tuned defaults from #10411 were measured on a GB10 / DGX Spark (128 GiB unified memory) and over-provisioned multi-GPU consumer Blackwell (e.g. 2x16 GiB RTX 50-series) into CUDA OOM during model init: - The Blackwell physical batch (512 -> 2048) sets both n_batch and n_ubatch. The compute buffer scales ~n_ubatch * n_ctx and is allocated PER DEVICE (it can't be split across GPUs), so a large context turns ub2048 into multi-GiB of scratch that must fit one 16 GiB card. - The VRAM-scaled parallel-slot default tiered off TotalAvailableVRAM(), which SUMS all GPUs (2x16 -> "32 GiB" -> 8 slots), but the allocations are per-device. Make both decisions per-device and context-aware: - xsysinfo.MinPerGPUVRAM() reports the smallest device's VRAM; localGPU() uses it so the parallel tier and batch guard reason about one card. - PhysicalBatchForContext(gpu, ctx) raises the batch only when the extra compute buffer fits VRAM/4 at this model's context (16 GiB crosses over ~174k ctx, 32 GiB ~349k; GB10 reports system RAM so it still clears it). - Apply hardware defaults AFTER runBackendHooks in SetDefaults so the GGUF-guessed context is resolved before the batch decision. - The distributed router gates the node batch the same way. Unified-memory devices (GB10, Apple) report system RAM as their single device's VRAM, so they keep the prefill win. Assisted-by: 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 PalethorpeandEttore Di Giacinto
|
e1994579f8 |
fix(pii): load default detectors at startup + add LOCALAI_PII_DEFAULT_DETECTORS (#10474)
pii_default_detectors was applied to the live config only by a live POST /api/settings (ApplyRuntimeSettings) — neither the startup loader nor the config file watcher read it back. So after a restart the persisted default detectors were dropped, and the cloud-proxy MITM listener (which resolves each intercept host's detectors once at start via ResolvePIIPolicy) came up with an empty set and forwarded intercepted traffic unredacted, even though the MITM model had pii.enabled:true and the defaults were on disk. Request-side default redaction broke the same way. - startup.go: loadRuntimeSettingsFromFile now applies pii_default_detectors, before startMITMIfConfigured, with env > file precedence. - config_file_watcher.go: apply pii_default_detectors on live file edits, matching the existing env-guard pattern used for the other fields. - settings endpoint: rebuild the MITM listener when pii_default_detectors changes (its per-host detector map is frozen at listener start), not only on a mitm_listen change — so toggling a default detector takes effect on cloud-proxy traffic immediately. - new LOCALAI_PII_DEFAULT_DETECTORS env var / CLI flag (WithPIIDefaultDetectors) so the default detector set can be pinned at boot for immutable deployments. Assisted-by: Claude:claude-opus-4-8 Claude-Code Signed-off-by: Richard Palethorpe <io@richiejp.com> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> |
||
|
Richard Palethorpe
|
7888067914 |
fix(settings): merge partial /api/settings updates instead of overwriting (#10463)
POST /api/settings rebuilt runtime_settings.json from only the request body, so a focused admin page that submits a single field wiped every other persisted setting. The Middleware proxy tab (mitm_listen) and detector table (pii_default_detectors), plus the MCP SetBranding tool (instance_name/instance_tagline), all POST partial bodies; the no-omitempty api_keys and pii_default_detectors fields even round-tripped as JSON null. Read the persisted settings and overlay only the fields the request set (RuntimeSettings.MergeNonNil) before writing. Every field is a pointer, so the reflection-based merge is total over the struct and any field added later is preserved automatically. Absent or null fields are now kept; clearing a setting is done by sending its explicit empty/zero value (api_keys [], mitm_listen "", etc.), unchanged from before. The full Settings page sends every field, so its Save behaves identically. Assisted-by: Claude:claude-opus-4-8 Claude-Code Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
fdf475ec5f |
feat(realtime): conversation compaction (summarize-then-drop) + OpenAI item.delete/truncate/clear (#10446)
* feat(realtime): add pipeline.compaction config + resolution Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(realtime): extract itemID helper, reuse in item.retrieve Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(realtime): drop duplicate Ginkgo bootstrap, fold specs into openai suite Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): implement conversation.item.delete Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): implement input_audio_buffer.clear Add a handler for the input_audio_buffer.clear client event that discards a partially-captured utterance (raw PCM + buffered Opus frames) via a unit-tested clearInputAudio helper, then acks with input_audio_buffer.cleared. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): implement conversation.item.truncate (text) Clears both .Text and .Transcript of the assistant content part at contentIndex so barge-in truncation also works for audio turns whose spoken words live in .Transcript. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): add Conversation.Memory + pair-safe compactionCut Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(realtime): compactionCut returns 0 for keep<=0 (no-cap sentinel, avoids panic) Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * style(realtime): gofmt compaction test helper closures Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): inject rolling memory into the prompt + summary builders Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): server-side summarize-then-drop compactor Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(realtime): unit-test prefixMatches eviction-safety predicate Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): resolve summarizer model + schedule compaction per turn Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(realtime): document conversation compaction + new item events Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(realtime): resolve summary model inside compaction goroutine (lazy, off-path) Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(realtime): reuse reasoning.ExtractReasoningComplete for summary stripping Replace the bespoke <think> regex in the compactor with the shared pkg/reasoning extractor (via spokenReasoningConfig), matching the rest of the realtime path and covering all reasoning tag families, not just <think>. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(config): register pipeline.compaction fields in meta registry TestAllFieldsHaveRegistryEntries requires every ModelConfig field to have a UI/meta registry entry; add the four pipeline.compaction.* leaves so they render with proper labels/descriptions instead of the reflection fallback. Assisted-by: Claude:claude-opus-4-8 [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> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
600dafd20b |
feat(ced): sound-event classification backend (CED audio tagger) (#10425)
* feat(ced): sketch sound-classification backend (CED audio tagger) Wires ced.cpp (CED, 527-class AudioSet sound-event tagger; baby cry, footsteps, glass, alarms, dog bark) into LocalAI as a Go/purego backend. SKETCH (backend skeleton real; core REST wiring + CI/gallery is a checklist in DESIGN.md): - backend/backend.proto: new SoundDetection rpc + SoundClass messages (run `make protogen-go` to regenerate pkg/grpc/proto). - backend/go/ced: main.go (purego dlopen libced.so + ced_capi.h), goced.go (Ced gRPC backend: Load + SoundDetection), Makefile (clone-at-pin CED_VERSION, ggml static-PIC shared build), run.sh, package.sh, .gitignore. - DESIGN.md: REST /v1/audio/classification wiring (handler/route/capability registration checklist), gallery/index + CI registration, and a scoping note for the realtime/websocket live-recognition path (sliding-window classify over the existing ws transport + voicegate; the ced C-API per-PCM entry point is already window-friendly). Backend code does not compile until protogen-go regenerates the pb types and a libced.so is built (Makefile clones+builds it). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ced): REST /v1/audio/classification endpoint + capability registration Wires the ced sound-event classification backend (AudioSet audio tagger) end to end through the REST surface, mirroring the transcription path. - Handler: core/http/endpoints/openai/sound_classification.go parses the multipart audio upload, temp-files it, resolves the model config and calls the SoundDetection RPC; returns {model, detections[]} JSON. - Backend wrapper: core/backend/sound_classification.go (ModelSoundDetection) loads the model and normalizes the proto response into schema types. - Schema: core/schema/sound_classification.go (SoundClassificationResult). - gRPC layer: SoundDetection wired through the LocalAI wrapper (interface, Backend client, Client, embed, server, base default) so the loader-typed client exposes the RPC; proto regenerated via make protogen-go. - Route: POST /v1/audio/classification (+ /audio/classification alias) with the audio/multipart default-model middleware in routes/openai.go. - Capability surfaces: swagger @Tags/@Router on the handler; FLAG_SOUND_ CLASSIFICATION usecase flag + UsecaseSoundClassification + UsecaseInfoMap + GuessUsecases + ModalityGroups + GetAllModelConfigUsecases; meta usecase option; /api/instructions audio area updated; auth RouteFeatureRegistry + FeatureAudioClassification (APIFeatures, default ON) + FeatureMetas; UI usecaseFilters, capabilities.js CAP_SOUND_CLASSIFICATION, Models.jsx filter + i18n; docs page features/audio-classification.md + whats-new + crosslink. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ced): realtime sound-event detection over the websocket API When a realtime pipeline configures a sound-classification model, each VAD-committed utterance (the same window the transcription path produces) is also run through the CED sound-event classifier and the scored AudioSet tags are emitted as a new server event. No new backend rpc is needed: the SoundDetection gRPC method already exists on this branch. - config: add Pipeline.SoundDetection (yaml/json sound_detection,omitempty) beside Transcription/VAD. - realtime: add Model.SoundDetection(ctx, audio, topK, threshold) to the ModelInterface; implement it on wrappedModel and transcriptOnlyModel by calling backend.ModelSoundDetection with the session's sound-classification model config (mirrors how Transcribe dispatches). Load the optional config in newModel / newTranscriptionOnlyModel; nil config keeps it additive. - types: add ConversationItemSoundDetectionEvent (item_id, content_index, detections[]{label,score,index}) with type conversation.item.sound_detection, its ServerEventType constant and MarshalJSON, mirroring the transcription completed event. - realtime: add emitSoundDetection (unary path: classify the committed window, build the event, t.SendEvent) and wire it at the utterance-commit hook right after emitTranscription; gated on session.SoundDetectionEnabled (resolved from Pipeline.SoundDetection at session setup, defaults top_k=5, threshold=0). Its error is logged via xlog but never aborts the turn. - test: Ginkgo specs for emitSoundDetection (tags emitted, empty detections, classifier error) plus a SoundDetection method on the fakeModel double. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(ced): implement SoundDetection in nodes backend test doubles The SoundDetection method added to the grpc backend interface left two test doubles (fakeBackendClient, fakeGRPCBackend) incomplete, so core/services/nodes failed to compile under `go vet`/`go test` (go build missed it: the doubles live in _test.go). Add the method to both, mirroring their existing Detect mock. Repairs CI for the nodes package. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ced): decouple realtime sound detection from VAD (sound-only sessions) Sound-event detection must activate on sounds, not speech, so it no longer runs through the voice VAD/transcription path. A sound-detection-only pipeline (sound_detection set, no transcription/LLM) now: - is accepted by prepareRealtimeConfig (sound_detection counts as a pipeline stage), - builds a lightweight model via newSoundDetectionOnlyModel (no VAD/STT/LLM/TTS loaded), and - defaults the session to turn_detection none (no VAD) with no transcription stage, so the client drives windowing via input_audio_buffer.commit (option A: client-side sliding window). The per-PCM C-API already supports arbitrary windows. commitUtterance gains a sound-only branch: it emits the conversation.item.sound_detection event (scored AudioSet tags) and stops - no transcription, no LLM response. generateResponse is now guarded on a transcription stage being present, so a sound-only turn never invokes the LLM. Existing transcription/VAD sessions are unchanged (additive). Added a commitUtterance sound-only Ginkgo spec asserting it emits the sound event and neither transcribes nor generates a response. go vet + golangci-lint (new-from-merge-base) clean; openai suite green. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ced): register sound-classification backend in gallery + CI Mechanical backend-image registration for the ced sound-event classifier, mirroring the parakeet-cpp Go/purego backend everywhere it is wired up. - .github/backend-matrix.yml: add the ced build matrix, field-for-field copies of the parakeet-cpp entries (cpu amd64/arm64, cublas cuda 12/13 amd64, l4t cuda-13 arm64, l4t-jetpack cuda-12 arm64, sycl f32/f16, vulkan amd64/arm64, rocm hipblas, and the metal darwin entry), changing only backend and tag-suffix. dockerfile stays ./backend/Dockerfile.golang. - backend/index.yaml: add the &ced meta anchor (capabilities map per platform) plus ced-development and the per-arch image entries, each uri/mirror tag-suffix matching the matrix exactly. The model gallery (GGUF) entry is intentionally deferred pending the HuggingFace publish (TODO note inline). - scripts/changed-backends.js: add an explicit item.backend === "ced" branch in inferBackendPath mapping to backend/go/ced/, same mechanism and ordering as the parakeet-cpp branch (before the generic golang fallthrough). - .github/workflows/bump_deps.yaml: register mudler/ced.cpp -> CED_VERSION in backend/go/ced/Makefile so the daily bot bumps the pin. - swagger/{docs.go,swagger.json,swagger.yaml}: regenerated via make swagger so the existing /v1/audio/classification annotations land in the generated spec. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ced): server-side windowing for realtime sound detection (option B) Adds an optional server-driven sliding-window classifier so a sound-only realtime client only has to stream audio (no input_audio_buffer.commit): - Pipeline.sound_detection_window_ms / sound_detection_hop_ms config knobs. When both > 0 on a sound-only session, the server classifies the last window of streamed audio every hop and emits a conversation.item.sound_ detection event; the input buffer is trimmed to one window so a long stream stays bounded. When unset, the session stays client-driven (option A). Runs independent of VAD (sound events are not speech). - handleSoundWindow (ticker) + classifySoundWindow (one tick, extracted so it is unit-testable) + writeWindowWAV, which declares the true InputSampleRate (NewWAVHeaderWithRate) so the classifier resamples correctly. Goroutine is started after toggleVAD and torn down with the session (close + wg.Wait). - Register pipeline.sound_detection (+window_ms/hop_ms) in the config meta registry; the earlier realtime commit added pipeline.sound_detection without a registry entry, failing TestAllFieldsHaveRegistryEntries. This fixes that and covers the two new knobs. Tests: classifySoundWindow emits an event + trims the buffer to one window, no-ops on too-little audio; writeWindowWAV declares the given sample rate. go build/vet + golangci-lint (new-from-merge-base) clean; config + openai suites green. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ced): add ced-base GGUF model gallery entries (f16 + q8_0) The ced-base weights are now published at mudler/ced-base-gguf (Apache-2.0, converted from mispeech/ced-base). Adds gallery/ced.yaml (backend: ced + known_usecases: sound_classification) and two gallery/index.yaml entries (ced-base-f16 default, ced-base-q8 smallest) with sha256-pinned files, and removes the now-resolved TODO from backend/index.yaml. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ced): add tiny/mini/small GGUF model gallery entries Publishes the rest of the CED family (same architecture, metadata-driven port verified end-to-end on ced-tiny) to mudler/ced-{tiny,mini,small}-gguf and adds their f16 + q8_0 gallery entries: ced-tiny (5.5M, edge/Pi-class) f16 11MB / q8_0 6MB ced-mini (9.6M) f16 19MB / q8_0 11MB ced-small (22M) f16 42MB / q8_0 23MB All sha256-pinned. ced-base remains the accuracy default. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ced): point gallery entries at the consolidated mudler/ced-gguf repo All CED quantizations (tiny/mini/small/base, f16/q8_0) now live in a single HuggingFace repo, mudler/ced-gguf, instead of per-model repos. Repoint the 8 gallery model entries' urls + file uris accordingly. sha256 and filenames are unchanged. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ced): bump CED_VERSION to the short-clip fix Pin the ced backend to ced.cpp 99c6ed3, which fixes a crash on any clip shorter than target_length (~10.11s): time_pos_embed was added at its full 63-frame grid instead of being sliced to the clip's actual time grid, tripping ggml_can_repeat in ggml_add. Surfaced by the live realtime e2e (sub-10s windows) and gated with a short-clip parity test upstream. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(ced): list ced.cpp as a LocalAI-team engine + backend-guide directive - README.md: add ced.cpp to the "native C/C++/GGML engines developed and maintained by the LocalAI project" table. - docs/content/features/backends.md: add a Sound Classification backend category (sound-event classification / audio tagging) listing ced.cpp. - .agents/adding-backends.md: add a "Documenting the backend" section and two verification-checklist items requiring new backends to be documented in the backends.md category list, and in-house native engines to be added to the README maintained-engines table. This directive was missing. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ced): repin CED_VERSION to the v0.1.0 release commit ced.cpp history was squashed into a single release commit (tagged v0.1.0), so the previous pin (99c6ed3) no longer exists upstream. Pin to c04ac14, the v0.1.0 release commit, so the backend builds against a commit that exists. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(ced): silence gosec G304/G103 + govet unsafeptr on audited paths - sound_classification.go: os.Create(dst) where dst = temp dir + path.Base of the upload (no traversal). #nosec G304, matching the depth-anything-cpp handler. - goced.go: reading a NUL-terminated C string from a libced-owned buffer. #nosec G103 (gosec) + //nolint:govet (golangci-lint's unsafeptr check), since the uintptr is a C-owned malloc'd buffer, not Go-GC memory. 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> |
||
|
|
32c47706ae |
feat(realtime): speaker-aware conversations - surface identity to client and LLM (#10424)
* feat(realtime): add voice_recognition enforce + identity config Add Enforce *bool and Identity *VoiceIdentityConfig to PipelineVoiceRecognition, plus EnforceGate/IdentityEnabled/ AnnounceEnabled/PersonalizeEnabled helpers. Enforce nil defaults to gating (backward compatible); identity surfacing is independent of the gate. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): add Speaker type and conversation.item.speaker event Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(realtime): split voiceGate into Resolve + authorize Split the speaker authorization into a Resolve step (embed once, produce a types.Speaker identity) and a pure authorize policy step, with a 0..100 confidence score mirroring /v1/voice/identify. The legacy Authorize wrapper is kept so existing specs stay green. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): resolve speaker per turn and emit conversation.item.speaker Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): personalize LLM turns with recognized speaker Set the per-message name field on each recognized user turn and append a current-speaker note to the system message, both gated by the voice recognition identity config. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(realtime): document speaker identity surfacing and personalization Document the new voice_recognition keys (enforce, identity.*) and the LocalAI-extension conversation.item.speaker server event in the realtime feature docs. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(realtime): cover when:first+identity re-resolution and multi-speaker history Add two integration specs to harden the speaker-aware realtime path: - when:first with an Identity block re-resolves the speaker every turn even though re-authorization is skipped after the first match: a later resolve error now fails closed, while a clean later resolve still surfaces and names the speaker. - multi-speaker history attribution: each user turn carries its own per-message name and the injected system note reflects the latest speaker. Test-only change; no production behavior was modified. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(realtime): surface speaker labels in conversation.item.speaker Carry the registered speaker's labels (identify mode) on types.Speaker so they flow into the conversation.item.speaker event and the stored item. Verify mode has no labels, so the field is omitted there. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test(e2e): cover conversation.item.speaker over a real websocket Add a realtime-pipeline-identity config (verify mode, enforce:false, identity announce+announce_unknown+personalize) and two e2e specs driving the real server over a real WebSocket with the mock VoiceEmbed backend: an authorized speaker yields a conversation.item.speaker event naming e2e-speaker (matched true) and reaches response.done; an unauthorized speaker yields an unknown (matched false, no name) event and still responds, proving enforce:false never drops a turn. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(config): register voice_recognition enforce + identity fields The meta registry coverage test (TestAllFieldsHaveRegistryEntries) requires every config field to have an entry in core/config/meta/registry.go. The new voice_recognition.enforce and voice_recognition.identity.* fields were missing, failing tests-linux and tests-apple. Add registry entries (toggles) so the fields are surfaced in the model-config editor and the coverage test passes. Assisted-by: Claude:claude-opus-4-8 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> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> |
||
|
Leoy
|
b50b1fe418 |
feat(watchdog): add size-aware LRU eviction mode (#9527)
* feat(watchdog): add size-aware LRU eviction mode When the model count hits the LRU limit or the memory reclaimer fires, evict the largest model by on-disk file size first rather than the least-recently-used one. For GGUF models the file size is a reliable proxy for GPU/RAM footprint, so evicting the largest candidate maximises freed memory per eviction round while keeping small utility models (embeddings, classifiers, rerankers) resident. Changes: - `pkg/model/watchdog.go`: add `sizeAwareEviction` flag and `modelSizes map[string]int64` to `WatchDog`; sort candidates by `sizeBytes` desc (LRU time as tiebreaker) when the flag is set; add `RegisterModelSize`, `SetSizeAwareEviction`, `GetSizeAwareEviction` - `pkg/model/watchdog_options.go`: add `WithSizeAwareEviction` option - `pkg/model/initializers.go`: stat model file after load and call `RegisterModelSize` so size data is available before the first eviction - `core/config/application_config.go`, `runtime_settings.go`: add `SizeAwareEviction` field and `WithSizeAwareEviction` app option; expose via `ToRuntimeSettings` / `ApplyRuntimeSettings` for the `POST /api/settings` live-reload path - `core/cli/run.go`: add `--size-aware-eviction` flag / `LOCALAI_SIZE_AWARE_EVICTION` env var - `core/application/startup.go`, `watchdog.go`: wire the new option through to `NewWatchDog` - `pkg/model/watchdog_test.go`: 5 new specs — option enable, dynamic toggle, largest-first ordering, equal-size LRU tiebreaker, no-size fallback to LRU, and size-map cleanup on eviction Closes #9375 Signed-off-by: supermario_leo <leo.stack@outlook.com> * refactor(watchdog): use vram estimation scaffolding for model size Replace the brittle os.Stat(modelFile) approach with a proper call to pkg/vram, which handles multi-file models (DownloadFiles, MMProj) and all weight file types, not just single GGUF files. - Add estimateModelSizeBytes() in core/backend/options.go that collects all weight file URIs from the model config, resolves them to file:// URIs, and calls vram.Estimate() with the shared DefaultCachedSizeResolver (15-min TTL cache avoids redundant stat calls on repeated loads) - Thread the result through via a new WithModelSizeBytes() loader option - In initializers.go, consume the pre-computed size instead of calling os.Stat; if no size was supplied (e.g. for external/router-dispatched models) the registration is simply skipped Signed-off-by: supermario_leo <leo.stack@outlook.com> * refactor(watchdog): use EstimateModel with HF fallback for size estimation Switch estimateModelSizeBytes from calling vram.Estimate directly to the unified vram.EstimateModel entry point, which adds automatic fallbacks: file-based GGUF metadata → HF API → size string. Also extract the HuggingFace repo ID from model URIs (huggingface://, hf://, https://huggingface.co/ and org/model short-form) and pass it as ModelEstimateInput.HFRepo, so models not yet downloaded locally can still get a size estimate via the HF API. Addresses @mudler's review feedback: "better to rely on EstimateModel and pass by the HF URL of the model extracted from the URI". Signed-off-by: supermario_leo <leo.stack@outlook.com> * feat(webui): add Size-Aware Eviction toggle to settings page The size-aware eviction setting was wired through the CLI flag and the RuntimeSettings live-reload path (POST /api/settings) but had no handle on the React settings page, so it could not be toggled from the UI. Add a Size-Aware Eviction toggle to the Watchdog section, next to the existing Force Eviction When Busy / LRU eviction handles. The settings page loads and saves the whole RuntimeSettings object, so the new size_aware_eviction key is picked up with no extra plumbing. Addresses @mudler's review feedback: the application config setting should land on the same UI settings page as the other handles. Signed-off-by: supermario_leo <leo.stack@outlook.com> --------- Signed-off-by: supermario_leo <leo.stack@outlook.com> |
||
|
LocalAI [bot]andEttore Di Giacinto
|
23f225260c |
refactor(config): single source of truth for default values (#10418)
refactor(config): single source of truth for default values across config + backend Defaults were decided in two areas with duplicated/drifted literals: the config SetDefaults tiers vs core/backend/options.go's grpcModelOpts (which translates a ModelConfig to the backend wire format and supplied its own fallbacks). They had drifted - n_gpu_layers 9999999 (options.go) vs 99999999 (gguf.go), two 512 batch constants, context 1024 (gguf) vs 4096 (backend) scattered as bare literals. Introduce core/config/defaults.go as the canonical home (DefaultContextSize=4096, GGUFFallbackContextSize=1024, DefaultNGPULayers=99999999, DefaultFlashAttention= auto). gguf.go / hooks_llamacpp.go use them directly; core/backend references them (backend imports config, never the reverse) so DefaultContextSize/DefaultBatchSize and the flash-attn / n_gpu_layers fallbacks resolve to one place. The two context values (1024 GGUF-no-estimate vs 4096 general) are kept distinct but now named + documented, not blind literals. Behavior-preserving; config + backend suites green. Assisted-by: Claude:opus-4.8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |