mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-08 15:28:23 -04:00
11cff1b309f669ab75c19258c0a512f779994de7
21 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
LocalAI [bot]
|
d77a9137d8 |
feat(llama-cpp): bump to MTP-merge SHA and automatically set MTP defaults (#9852)
* feat(llama-cpp): bump to MTP-merge SHA and document draft-mtp spec type Update LLAMA_VERSION to 0253fb21 (post ggml-org/llama.cpp#22673 merge, 2026-05-16) to pick up Multi-Token Prediction support. No grpc-server.cpp changes are required: the existing `spec_type` option delegates to upstream's `common_speculative_types_from_names()`, which already accepts the new `draft-mtp` name. The `n_rs_seq` cparam needed by MTP is auto-derived inside `common_context_params_to_llama` from `params.speculative.need_n_rs_seq()`, and when no `draft_model` is set the upstream server builds the MTP context off the target model itself. Docs: extend the speculative-decoding section of the model-configuration guide with the new type, both load paths (MTP head embedded in the main GGUF vs. separate `mtp-*.gguf` sibling), the PR's recommended `spec_n_max:2-3`, and the chained `draft-mtp,ngram-mod` recipe. Also notes that the upstream `-hf` auto-discovery of `mtp-*.gguf` siblings is not wired through LocalAI's gRPC layer. Agent guide: short note explaining that new upstream spec types are picked up automatically and that MTP needs no gRPC plumbing. Assisted-by: Claude:claude-opus-4-7 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(llama-cpp): auto-detect MTP heads and enable draft-mtp on import + load Detect upstream's `<arch>.nextn_predict_layers` GGUF metadata key (set by `convert_hf_to_gguf.py` for Qwen3.5/3.6 family models and similar) and, when present and the user has not configured a `spec_type` explicitly, auto-append the upstream-recommended speculative-decoding tuple: - spec_type:draft-mtp - spec_n_max:6 - spec_p_min:0.75 The 0.75 p_min is pinned defensively because upstream marks the current default with a "change to 0.0f" TODO; locking it here keeps acceptance thresholds stable across future llama.cpp bumps. Detection runs in two places: - The model importer (`POST /models/import-uri`, the `/import-model` UI) range-fetches the GGUF header for HuggingFace / direct-URL imports via `gguf.ParseGGUFFileRemote`, with a 30s timeout and non-fatal error handling. OCI/Ollama URIs are skipped because the artifact is not directly streamable; the load-time hook covers them once the file is on disk. - The llama-cpp load-time hook (`guessGGUFFromFile`) reads the local header on every model start and appends the same options if `spec_type` is not already set. Both paths share `ApplyMTPDefaults` and respect an explicit user-set `spec_type:` / `speculative_type:` so YAML overrides win. Ginkgo specs cover the append, preserve-user-choice, legacy alias, and nil safety paths. Assisted-by: Claude:claude-opus-4-7 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(importer): resolve huggingface:// URIs before MTP header probe `gguf.ParseGGUFFileRemote` only speaks HTTP(S), but the importer was handing it the raw `huggingface://...` URI directly (and similarly for any other custom downloader scheme). Live-test against `huggingface://ggml-org/Qwen3.6-27B-MTP-GGUF/Qwen3.6-27B-MTP-Q8_0.gguf` exposed this: the probe failed with `unsupported protocol scheme "huggingface"`, was caught by the non-fatal error path, and the MTP options were silently never applied to the generated YAML. Route every candidate URI through `downloader.URI.ResolveURL()` and require the resolved form to be HTTP(S). After the fix the probe successfully reads `<arch>.nextn_predict_layers=1` from the real HF GGUF and the emitted ConfigFile carries spec_type:draft-mtp, spec_n_max:6, spec_p_min:0.75 as intended. Assisted-by: Claude:claude-opus-4-7 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Richard Palethorpe
|
0245b33eab |
feat(realtime): Add Liquid Audio s2s model and assistant mode on talk page (#9801)
* feat(liquid-audio): add LFM2.5-Audio any-to-any backend + realtime_audio usecase
Wires LiquidAI's LFM2.5-Audio-1.5B as a self-contained Realtime API model:
single engine handles VAD, transcription, LLM, and TTS in one bidirectional
stream — drop-in alternative to a VAD+STT+LLM+TTS pipeline.
Backend
- backend/python/liquid-audio/ — new Python gRPC backend wrapping the
`liquid-audio` package. Modes: chat / asr / tts / s2s, voice presets,
Load/Predict/PredictStream/AudioTranscription/TTS/VAD/AudioToAudioStream/
Free and StartFineTune/FineTuneProgress/StopFineTune. Runtime monkey-patch
on `liquid_audio.utils.snapshot_download` so absolute local paths from
LocalAI's gallery resolve without a HF round-trip. soundfile in place of
torchaudio.load/save (torchcodec drags NVIDIA NPP we don't bundle).
- backend/backend.proto + pkg/grpc/{backend,client,server,base,embed,
interface}.go — new AudioToAudioStream RPC mirroring AudioTransformStream
(config/frame/control oneof in; typed event+pcm+meta out).
- core/services/nodes/{health_mock,inflight}_test.go — add stubs for the
new RPC to the test fakes.
Config + capabilities
- core/config/backend_capabilities.go — UsecaseRealtimeAudio, MethodAudio
ToAudioStream, UsecaseInfoMap entry, liquid-audio BackendCapability row.
- core/config/model_config.go — FLAG_REALTIME_AUDIO bitmask, ModalityGroups
membership in both speech-input and audio-output groups so a lone flag
still reads as multimodal, GetAllModelConfigUsecases entry, GuessUsecases
branch.
Realtime endpoint
- core/http/endpoints/openai/realtime.go — extract prepareRealtimeConfig()
so the gate is unit-testable; accept realtime_audio models and self-fill
empty pipeline slots with the model's own name (user-pinned slots win).
- core/http/endpoints/openai/realtime_gate_test.go — six specs covering nil
cfg, empty pipeline, legacy pipeline, self-contained realtime_audio,
user-pinned VAD slot, and partial legacy pipeline.
UI + endpoints
- core/http/routes/ui.go — /api/pipeline-models accepts either a legacy
VAD+STT+LLM+TTS pipeline or a realtime_audio model; surfaces a
self_contained flag so the Talk page can collapse the four cards.
- core/http/routes/ui_api.go — realtime_audio in usecaseFilters.
- core/http/routes/ui_pipeline_models_test.go — covers both code paths.
- core/http/react-ui/src/pages/Talk.jsx — self-contained badge instead of
the four-slot grid; rename Edit Pipeline → Edit Model Config; less
pipeline-specific wording.
- core/http/react-ui/src/pages/Models.jsx + locales/en/models.json — new
realtime_audio filter button + i18n.
- core/http/react-ui/src/utils/capabilities.js — CAP_REALTIME_AUDIO.
- core/http/react-ui/src/pages/FineTune.jsx — voice + validation-dataset
fields, surfaced when backend === liquid-audio, plumbed via
extra_options on submit/export/import.
Gallery + importer
- gallery/liquid-audio.yaml — config template with known_usecases:
[realtime_audio, chat, tts, transcript, vad].
- gallery/index.yaml — four model entries (realtime/chat/asr/tts) keyed by
mode option. Fixed pre-existing `transcribe` typo on the asr entry
(loader silently dropped the unknown string → entry never surfaced as a
transcript model).
- gallery/lfm.yaml — function block for the LFM2 Pythonic tool-call format
`<|tool_call_start|>[name(k="v")]<|tool_call_end|>` matching
common_chat_params_init_lfm2 in vendored llama.cpp.
- core/gallery/importers/{liquid-audio,liquid-audio_test}.go — detector
matches LFM2-Audio HF repos (excludes -gguf mirrors); mode/voice
preferences plumbed through to options.
- core/gallery/importers/importers.go — register LiquidAudioImporter
before LlamaCPPImporter.
- pkg/functions/parse_lfm2_test.go — seven specs for the response/argument
regex pair on the LFM2 pythonic format.
Build matrix
- .github/backend-matrix.yml — seven liquid-audio targets (cuda12, cuda13,
l4t-cuda-13, hipblas, intel, cpu amd64, cpu arm64). Jetpack r36 cuda-12
is skipped (Ubuntu 22.04 / Python 3.10 incompatible with liquid-audio's
3.12 floor).
- backend/index.yaml — anchor + 13 image entries.
- Makefile — .NOTPARALLEL, prepare-test-extra, test-extra,
docker-build-liquid-audio.
Docs
- .agents/plans/liquid-audio-integration.md — phased plan; PR-D (real
any-to-any wiring via AudioToAudioStream), PR-E (mid-audio tool-call
detector), PR-G (GGUF entries once upstream llama.cpp PR #18641 lands)
remain.
- .agents/api-endpoints-and-auth.md — expand the capability-surface
checklist with every place a new FLAG_* needs to be registered.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): function calling + history cap for any-to-any models
Three pieces, all on the realtime_audio path that just landed:
1. liquid-audio backend (backend/python/liquid-audio/backend.py):
- _build_chat_state grows a `tools_prelude` arg.
- new _render_tools_prelude parses request.Tools (the OpenAI Chat
Completions function array realtime.go already serialises) and
emits an LFM2 `<|tool_list_start|>…<|tool_list_end|>` system turn
ahead of the user history. Mirrors gallery/lfm.yaml's `function:`
template so the model sees the same prompt shape whether served
via llama-cpp or here. Without this the backend silently dropped
tools — function calling was wired end-to-end on the Go side but
the model never saw a tool list.
2. Realtime history cap (core/http/endpoints/openai/realtime.go):
- Session grows MaxHistoryItems int; default picked by new
defaultMaxHistoryItems(cfg) — 6 for realtime_audio models (LFM2.5
1.5B degrades quickly past a handful of turns), 0/unlimited for
legacy pipelines composing larger LLMs.
- triggerResponse runs conv.Items through trimRealtimeItems before
building conversationHistory. Helper walks the cut left if it
would orphan a function_call_output, so tool result + call pairs
stay intact.
- realtime_gate_test.go: specs for defaultMaxHistoryItems and
trimRealtimeItems (zero cap, under cap, over cap, tool-call pair
preservation).
3. Talk page (core/http/react-ui/src/pages/Talk.jsx):
- Reuses the chat page's MCP plumbing — useMCPClient hook,
ClientMCPDropdown component, same auto-connect/disconnect effect
pattern. No bespoke tool registry, no new REST endpoints; tools
come from whichever MCP servers the user toggles on, exactly as
on the chat page.
- sendSessionUpdate now passes session.tools=getToolsForLLM(); the
update re-fires when the active server set changes mid-session.
- New response.function_call_arguments.done handler executes via
the hook's executeTool (which round-trips through the MCP client
SDK), then replies with conversation.item.create
{type:function_call_output} + response.create so the model
completes its turn with the tool output. Mirrors chat's
client-side agentic loop, translated to the realtime wire shape.
UI changes require a LocalAI image rebuild (Dockerfile:308-313 bakes
react-ui/dist into the runtime image). Backend.py changes can be
swapped live in /backends/<id>/backend.py + /backend/shutdown.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): LocalAI Assistant ("Manage Mode") for the Talk page
Mirrors the chat-page metadata.localai_assistant flow so users can ask the
realtime model what's loaded / installed / configured. Tools are run
server-side via the same in-process MCP holder that powers the chat
modality — no transport switch, no proxy, no new wire protocol.
Wire:
- core/http/endpoints/openai/realtime.go:
- RealtimeSessionOptions{LocalAIAssistant,IsAdmin}; isCurrentUserAdmin
helper mirrors chat.go's requireAssistantAccess (no-op when auth
disabled, else requires auth.RoleAdmin).
- Session grows AssistantExecutor mcpTools.ToolExecutor.
- runRealtimeSession, when opts.LocalAIAssistant is set: gate on admin,
fail closed if DisableLocalAIAssistant or the holder has no tools,
DiscoverTools and inject into session.Tools, prepend
holder.SystemPrompt() to instructions.
- Tool-call dispatch loop: when AssistantExecutor.IsTool(name), run
ExecuteTool inproc, append a FunctionCallOutput to conv.Items, skip
the function_call_arguments client emit (the client can't execute
these — it doesn't know about them). After the loop, if any
assistant tool ran, trigger another response so the model speaks the
result. Mirrors chat's agentic loop, driven server-side rather than
via client round-trip.
- core/http/endpoints/openai/realtime_webrtc.go: RealtimeCallRequest
gains `localai_assistant` (JSON omitempty). Handshake calls
isCurrentUserAdmin and builds RealtimeSessionOptions.
- core/http/react-ui/src/pages/Talk.jsx: admin-only "Manage Mode"
checkbox under the Tools dropdown; passes localai_assistant: true to
realtimeApi.call's body, captured in the connect callback's deps.
Mirroring chat's pattern means the in-process MCP tools surface "just
works" for the Talk page without exposing a Streamable-HTTP MCP endpoint
(which was the alternative). Clients with their own MCP servers can
still use the existing ClientMCPDropdown path in parallel; the realtime
handler distinguishes them by AssistantExecutor.IsTool() at dispatch
time.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): render Manage Mode tool calls in the Talk transcript
Previously the realtime endpoint only emitted response.output_item.added
for the FunctionCall item, and Talk.jsx's switch ignored the event — so
server-side tool runs were invisible in the UI. The model would speak
the result but the user had no way to see what tool was actually
called.
realtime.go: after executing an assistant tool inproc, emit a second
output_item.added/.done pair for the FunctionCallOutput item. Mirrors
the way the chat page displays tool_call + tool_result blocks.
Talk.jsx: handle both response.output_item.added and .done. Render
FunctionCall (with arguments) and FunctionCallOutput (pretty-printed
JSON when possible) as two transcript entries — `tool_call` with the
wrench icon, `tool_result` with the clipboard icon, both in mono-space
secondary-colour. Resets streamingRef after the result so the next
assistant text delta starts a fresh transcript entry instead of
appending to the previous turn.
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* refactor(realtime): bound the Manage Mode tool-loop + preserve assistant tools
Fallout from a review pass on the Manage Mode patches:
- Bound the server-side agentic loop. triggerResponse used to recurse on
executedAssistantTool with no cap — a model that kept calling tools
would blow the goroutine stack. New maxAssistantToolTurns = 10 (mirrors
useChat.js's maxToolTurns). Public triggerResponse is now a thin shim
over triggerResponseAtTurn(toolTurn int); recursion increments the
counter and stops at the cap with an xlog.Warn.
- Preserve Manage Mode tools across client session.update. The handler
used to blindly overwrite session.Tools, so toggling a client MCP
server mid-session silently wiped the in-process admin tools. Session
now caches the original AssistantTools slice at session creation and
the session.update handler merges them back in (client names win on
collision — the client is explicit).
- strconv.ParseBool for the localai_assistant query param instead of
hand-rolled "1" || "true". Mirrors LocalAIAssistantFromMetadata.
- Talk.jsx: render both tool_call and tool_result on
response.output_item.done instead of splitting them across .added and
.done. The server's event pairing (added → done) stays correct; the
UI just doesn't need to inspect both phases of the same item. One
switch case instead of two, no behavioural change.
Out of scope (noted for follow-ups): extract a shared assistant-tools
helper between chat.go and realtime.go (duplication is small enough
that two parallel implementations stay readable for now), and an i18n
key for the Manage Mode helper text (Talk.jsx doesn't use i18n
anywhere else yet).
Assisted-by: claude-code:claude-opus-4-7-1m [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* ci(test-extra): wire liquid-audio backend smoke test
The backend ships test.py + a `make test` target and is listed in
backend-matrix.yml, so scripts/changed-backends.js already writes a
`liquid-audio=true|false` output when files under backend/python/liquid-audio/
change. The workflow just wasn't reading it.
- Expose the `liquid-audio` output on the detect-changes job
- Add a tests-liquid-audio job that runs `make` + `make test` in
backend/python/liquid-audio, gated on the per-backend detect flag
The smoke covers Health() and LoadModel(mode:finetune); fine-tune mode
short-circuits before any HuggingFace download (backend.py:192), so the
job needs neither weights nor a GPU. The full-inference path remains
gated on LIQUID_AUDIO_MODEL_ID, which CI doesn't set.
The four new Go test files (core/gallery/importers/liquid-audio_test.go,
core/http/endpoints/openai/realtime_gate_test.go,
core/http/routes/ui_pipeline_models_test.go, pkg/functions/parse_lfm2_test.go)
are already picked up by the existing test.yml workflow via `make test` →
`ginkgo -r ./pkg/... ./core/...`; their packages all carry RunSpecs entries.
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
|
||
|
LocalAI [bot]
|
d892e4af80 |
feat: add ds4 backend (DeepSeek V4 Flash) with tool calls, thinking, KV cache (#9758)
* test(e2e-backends): allow BACKEND_BINARY for native-built backends
Adds an escape hatch for hardware-gated backends (e.g. ds4) where the
model is too large for Docker build context. When BACKEND_BINARY points
at a run.sh produced by 'make -C backend/cpp/<name> package', the suite
skips docker image extraction and drives the binary directly.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* test(e2e-backends): validate BACKEND_BINARY basename + log actual source
Two follow-ups from the
|
||
|
Richard Palethorpe
|
969005b2a1 |
feat(gallery): Speed up load times and clean gallery entries (#9211)
* feat: Rework VRAM estimation and use known_usecases in gallery Signed-off-by: Richard Palethorpe <io@richiejp.com> Assisted-by: Claude:claude-opus-4-7[1m] [Claude Code] * chore(gallery): regenerate gallery index and add known_usecases to model entries Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> |
||
|
LocalAI [bot]
|
6d56bf98fe |
feat(importers): add vibevoice-cpp importer for GGUF bundles (#9685)
Routes mudler/vibevoice.cpp-models and similar repos to the vibevoice-cpp
backend. Detects via repo name ("vibevoice.cpp"/"vibevoice-cpp"), file
listing (vibevoice-*.gguf + tokenizer.gguf), or preferences.backend
override. Defaults to the realtime TTS model; preferences.usecase=asr
selects the ASR/diarization variant. Bundles the required tokenizer.gguf
and (for TTS) a voice prompt, emitting the Options[] entries the backend
expects. Registered ahead of VibeVoiceImporter so the C++ bundles aren't
swallowed by the older Python-backend substring match.
Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Write] [Bash]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
|
||
|
Ettore Di Giacinto
|
8452068f43 |
feat(importers): whisper.cpp HF repos pick a quant + nest under whisper/models (#9630)
The WhisperImporter's Import() switch ordered LooksLikeURL ahead of the HuggingFace branch, so any https://huggingface.co/<owner>/<repo> URI (e.g. LocalAI-io/whisper-large-v3-it-yodas-only-ggml) hijacked the URL path. FilenameFromUrl returned the repo slug, the gallery entry pointed at the HTML repo page, the SHA256 was empty, and the HF file listing was effectively dead code for HTTPS imports. The HF branch only fired for huggingface://owner/repo and hf://owner/repo references. Gate the URL case on a "ggml-*.bin" basename signal — mirroring how the llama-cpp importer gates on ".gguf" — so direct file URLs still take the URL path while HF repo URLs fall through to the HF branch. There the file listing is actually consulted: every ggml-*.bin entry is collected and one is picked by the new preferences.quantizations preference (default q5_0; comma-separated for fallback ordering). Pin the chosen file under whisper/models/<name>/<file> so a single repo can ship q4_0/q5_0/q8_0 side-by-side without colliding on disk, matching the llama-cpp/models/<name>/ layout. The fallback when no preference matches is the last available ggml file, mirroring llama-cpp's pickPreferredGroup behaviour. Tests: replace the previous probe spec with positive assertions against LocalAI-io/whisper-large-v3-it-yodas-only-ggml (default → ggml-model-q5_0.bin, quantizations=q4_0 → ggml-model-q4_0.bin) plus two offline specs that build a fake hfapi.ModelDetails to cover the fallback rule and non-ggml filtering without touching the network. Assisted-by: Claude:claude-opus-4-7 [Bash Read Edit WebFetch] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
c1f923b2bc |
fix(importer): emit all shards for multi-part GGUF models (#9513)
The llama-cpp HuggingFace importer iterated files one at a time and kept overwriting `lastGGUFFile`, so sharded repos such as `unsloth/Kimi-K2.6-GGUF` (14 `Q8_K_XL` parts) produced a gallery entry pointing only at the final shard — useless to llama.cpp's split loader, which needs shard 1 to discover the set. Group shards up front via new helpers in `pkg/huggingface-api` (`SplitShardSuffix`, `ShardGroup`, `GroupShards`). The llama-cpp importer now picks a group (preferred quant, then last-group fallback) and emits every shard, with `Model:` pointing at shard 1. `FindPreferredModelFile` returns shard 1 of the first matching group so the gallery agent's preview stays coherent for sharded repos. Adds unit coverage for the HuggingFace branch of the importer (which had none), plus shard-detection tests in the hfapi package. Assisted-by: Claude:Opus-4.7 [Read] [Edit] [Bash] |
||
|
Ettore Di Giacinto
|
f0c92610a1 |
feat(importer): expand importer flow to almost all backends (#9466)
* docs(agents): require importer integration when adding backends
Document the importer registry workflow so contributors know that adding
a new backend also requires updating the /import-model dropdown source:
either a new importer in core/gallery/importers/, extending an existing
one for drop-in replacements, or the pref-only slice for backends with
no reliable auto-detect signal. Always covered by a table-driven test.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for Batch 0 primitives
Introduce failing tests that drive Batch 0 of the importer expansion:
- pkg/huggingface-api: assert GetModelDetails populates PipelineTag and
LibraryName from /api/models/{repo}, and that a failing metadata
endpoint still returns file details (best-effort fetch).
- core/gallery/importers/helpers_test.go: new table-driven coverage for
HasFile, HasExtension, HasONNX, HasONNXConfigPair, HasGGMLFile.
- core/gallery/importers/importers_test.go: assert ErrAmbiguousImport
sentinel exists and round-trips through errors.Is.
- core/gallery/importers/local_test.go: extend with detection cases for
ggml-*.bin (whisper), silero_vad.onnx (silero-vad), and the piper
.onnx + .onnx.json pair.
- core/http/endpoints/localai/import_model_test.go: assert
ImportModelURIEndpoint returns HTTP 400 with a structured
{error, detail, hint} body when ErrAmbiguousImport surfaces.
All tests fail in the expected places (missing fields, missing
helpers, missing sentinel, endpoint still wraps as 500).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): Batch 0 foundation — helpers, sentinel, local detection
Implements the Batch 0 primitives that subsequent importer batches build on:
- pkg/huggingface-api: ModelDetails gains PipelineTag and LibraryName.
GetModelDetails now layers a best-effort GET /api/models/{repo} fetch
on top of ListFiles — a metadata outage leaves the fields empty but
still returns full file details. Uses a dedicated response struct
because the single-model endpoint uses snake_case keys while the list
endpoint historically returned camelCase.
- core/gallery/importers/helpers.go: generic HasFile, HasExtension,
HasONNX, HasONNXConfigPair, HasGGMLFile helpers working on
[]hfapi.ModelFile so per-backend importers can detect artefact
patterns without duplicating string wrangling.
- core/gallery/importers/importers.go: adds the ErrAmbiguousImport
sentinel. DiscoverModelConfig now returns it (wrapped with
fmt.Errorf("%w: ...")) when no importer matched AND the HF
pipeline_tag falls in a whitelist of narrow modalities (ASR, TTS,
sentence-similarity, text-classification, object-detection). The
whitelist is intentionally narrow — unknown tags keep the previous
"no importer matched" behaviour to avoid blocking rare repos.
- core/gallery/importers/local.go: three new local-path detections,
inserted before the existing merged-transformers branch:
* ggml-*.bin → whisper
* silero*.onnx → silero-vad
* *.onnx + *.onnx.json pair → piper
- core/http/endpoints/localai/import_model.go: ImportModelURIEndpoint
surfaces ErrAmbiguousImport as HTTP 400 with
{error, detail, hint} JSON, preserving existing behaviour for
unrelated errors.
Green tests:
go test ./core/gallery/importers/... ./pkg/huggingface-api/... \
./core/http/endpoints/localai/...
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(importers): red tests for KnownBackend endpoint and importer metadata
Add failing tests that drive Batch UI-Dropdown:
- importers_test.go: assert importers expose Name/Modality/AutoDetects
and that LlamaCPPImporter advertises drop-in replacements via a new
AdditionalBackendsProvider interface. A Registry() accessor is also
expected.
- backend_test.go (new): assert GET /backends/known returns
[]schema.KnownBackend, covers every importer, exposes drop-in
llama-cpp replacements, includes curated pref-only backends, has no
duplicates, and is sorted by Modality+Name.
These tests fail at compile time against master; they are intentionally
red so the follow-up green commit is reviewable.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery): add /backends/known endpoint for importer-aware backend list
Extend the Importer interface with Name/Modality/AutoDetects so the
import system can self-describe its registry, and introduce the
AdditionalBackendsProvider interface so importers can advertise drop-in
replacements (llama-cpp advertises ik-llama-cpp and turboquant).
Expose the new GET /backends/known endpoint that merges:
- the importer registry (auto-detect supported),
- drop-in replacements hosted by importers (preference-only),
- a curated knownPrefOnlyBackends slice for backends with no dedicated
importer (sglang, tinygrad, trl, mlx-vlm, whisperx, kokoros, Qwen TTS
variants, sam3-cpp) — kept at the top of backend.go so contributors
adding a new pref-only backend have one obvious place to edit,
- backends installed on disk but unknown to the importer (marked
AutoDetect=false, empty Modality).
The endpoint deliberately does NOT filter by gallery membership or host
capability (unlike /backends/available): LocalAI may auto-install a
backend that is not yet present, so the import form dropdown must show
everything the importer knows about.
Response is deduplicated (importer wins over pref-only) and sorted by
Modality+Name for deterministic output.
Registered in core/http/routes/localai.go next to /backends/available
under the same admin middleware.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui): source import form backend dropdown from /backends/known
Replace the hard-coded BACKENDS constant in ImportModel.jsx with a
live fetch of /backends/known on mount. Users now see every backend
the importer layer knows about (including preference-only entries)
grouped by modality, not a stale subset.
Changes:
- config.js: add backendsKnown endpoint constant next to
backendsAvailable.
- api.js: add backendsApi.listKnown() wrapper.
- ImportModel.jsx: remove BACKENDS constant, fetch the list via
useEffect, and derive grouped options via buildBackendOptions.
Preference-only entries render with a " (preference-only)" suffix.
Loading state disables the dropdown with a "Loading backends…"
placeholder; on fetch failure the form falls back to auto-detect
only and surfaces a non-blocking toast.
- SearchableSelect.jsx: accept items flagged isHeader=true and render
them as non-selectable section dividers. Keyboard navigation skips
headers and search queries hide them so filtered output stays
relevant.
Vitest is not set up in this project (devDependencies ship Playwright
only). Per the brief's guard-rail, no frontend test framework is
introduced; coverage is provided by the Go handler tests that assert
the /backends/known contract consumed by the React form.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for whisper importer
Asserts detection on ggerganov/whisper.cpp (via ggml-*.bin filename),
the preferences.backend=whisper override path for arbitrary URIs,
and the Importer interface metadata (name/modality/autodetect).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add whisper importer
Recognises whisper.cpp GGML models by the "ggml-*.bin" filename
convention (direct URL or HF repo member) and by the explicit
preferences.backend="whisper" override. Emits backend: whisper with
the transcript use-case. Registered before llama-cpp so the narrow
filename signal wins before any generic GGUF match is attempted.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for moonshine importer
Asserts detection on UsefulSensors/moonshine-tiny via owner + ONNX
files, the preferences.backend=moonshine override for arbitrary URIs,
and the Importer interface metadata (name/modality/autodetect).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add moonshine importer
Matches UsefulSensors-owned HF repos whose artefacts or metadata
identify them as ASR: on-disk .onnx files (the canonical Moonshine
packaging) OR pipeline_tag=automatic-speech-recognition (covers
transformers/safetensors-only sibling repos). preferences.backend=
moonshine overrides detection. Test uses the live moonshine-tiny
repo because the canonical UsefulSensors/moonshine repo currently
hits a recursive-subfolder bug in pkg/huggingface-api ListFiles.
Registered after WhisperImporter but before LlamaCPPImporter and
TransformersImporter so the narrower owner+ASR signal wins before
the generic tokenizer.json check routes the repo to transformers.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for nemo importer
Asserts detection on nvidia/parakeet-tdt-0.6b-v3 via owner + .nemo
file, the preferences.backend=nemo override for arbitrary URIs, and
the Importer interface metadata (name/modality/autodetect).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add nemo importer
Matches nvidia-owned HF repos that ship a .nemo checkpoint archive,
the canonical NeMo ASR packaging. preferences.backend=nemo forces
detection. Registered between moonshine and llama-cpp so the narrow
owner + extension signal wins before any downstream generic matcher.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for faster-whisper importer
Asserts detection on Systran/faster-whisper-large-v3 (owner +
model.bin + config.json + ASR pipeline), the preferences.backend=
faster-whisper override for arbitrary URIs, and the Importer
interface metadata.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add faster-whisper importer
Recognises CTranslate2-packaged whisper checkpoints distributed for
the faster-whisper runtime: model.bin + config.json + ASR
pipeline_tag, narrowed to Systran-owned repos or repo names
containing "faster-whisper" to avoid falsely claiming vanilla
OpenAI whisper HF repos. preferences.backend=faster-whisper
overrides detection. Registered before llama-cpp and transformers
so the narrow signal wins before tokenizer.json routes the repo to
the generic transformers importer.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for qwen-asr importer
Asserts detection on Qwen/Qwen3-ASR-1.7B via owner + ASR substring
in the repo name, the preferences.backend=qwen-asr override for
arbitrary URIs, and the Importer interface metadata.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add qwen-asr importer
Matches Qwen-owned HF repos whose name contains "ASR"
(case-insensitive), routing them to the qwen-asr backend rather
than the generic transformers/vllm path. The substring check scans
the repo portion only so the owner field cannot leak a false match.
preferences.backend=qwen-asr forces detection. Registered before
llama-cpp and transformers so the narrow owner+name signal wins.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): ASR ambiguity surfaces ErrAmbiguousImport
Locks in the behaviour added in Batch 0: an HF repo whose pipeline_tag
marks it as automatic-speech-recognition but whose artefacts match no
ASR importer (and no generic importer) must fail with
ErrAmbiguousImport so callers know to pass preferences.backend rather
than silently guess. pyannote/voice-activity-detection is the fixture
— its file list is only config.yaml + README, leaving every importer's
artefact check negative.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for piper importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add piper importer
Detects piper TTS voices by the canonical <voice>.onnx + <voice>.onnx.json
pair packaging (via HasONNXConfigPair). Narrow enough to skip generic
ONNX repos used by other backends (Moonshine ASR, sentence-transformers).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for bark importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add bark importer
Detects Suno's Bark TTS checkpoints by HF owner "suno" + repo name
prefix "bark". Adds HFOwnerRepoFromURI() helper so importers can fall
back to URI parsing when pkg/huggingface-api's recursive tree listing
errors on repos with nested subdirectories (suno/bark ships a
speaker_embeddings/v2 subtree that trips a pre-existing path-doubling
bug in the listFilesInPath recursion).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for fish-speech importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add fish-speech importer
Detects Fish Audio TTS releases by HF owner "fishaudio" with a URI-based
fallback for repos whose tree recursion trips the pre-existing hfapi
path-doubling bug.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for outetts importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add outetts importer
Detects OuteAI's OuteTTS releases by HF owner "OuteAI" or a case-
insensitive "OuteTTS" substring in the repo name, with a URI-based
fallback for recursion-bugged repos.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for voxcpm importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add voxcpm importer
Detects OpenBMB's VoxCPM TTS family by repo-name substring (community
mirrors re-host the weights under many owners — mlx-community,
bluryar, callgg, etc).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for kokoro importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add kokoro importer
Detects hexgrad's Kokoro TTS by the "Kokoro" repo-name substring paired
with a PyTorch .pth/.pt checkpoint — the pairing excludes ONNX-only
mirrors (handled by the pref-only `kokoros` Rust runtime) and GGUF
mirrors (handled by llama-cpp).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for kitten-tts importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add kitten-tts importer
Detects KittenML's kitten-tts releases by owner or "kitten-tts" repo-name
substring, with URI-parsing fallback.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for neutts importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add neutts importer
Detects Neuphonic's NeuTTS releases by owner "neuphonic" or "neutts"
repo-name substring, with URI-parsing fallback.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for chatterbox importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add chatterbox importer
Detects Resemble AI's Chatterbox TTS by owner "ResembleAI" or
"chatterbox" repo-name substring, with URI-parsing fallback.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for vibevoice importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add vibevoice importer
Detects Microsoft's VibeVoice TTS by "vibevoice" repo-name substring
(case-insensitive) so community mirrors still route here.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for coqui importer
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add coqui importer
Detects Coqui AI's TTS releases (XTTS-v2, YourTTS, …) by the
authoritative `coqui` HF owner, with URI-parsing fallback.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): TTS ambiguity surfaces ErrAmbiguousImport
Adds a Ginkgo spec that imports nari-labs/Dia-1.6B — a real HF repo
carrying pipeline_tag="text-to-speech" whose artefacts (*.pth, one
safetensors shard, preprocessor_config.json, config.json) match none of
the Batch-2 TTS importers nor the generic text/image importers — and
asserts DiscoverModelConfig wraps ErrAmbiguousImport via errors.Is.
Also pivots the endpoint-level ambiguity fixture from hexgrad/Kokoro-82M
to nari-labs/Dia-1.6B. Batch 2 added a dedicated kokoro importer that
now claims the original fixture; Dia remains genuinely unclaimed and
so exercises the same ambiguity code path at the HTTP layer.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for stablediffusion-ggml importer
Covers HF repo detection (city96/FLUX.1-dev-gguf), raw .gguf URL matching on
filename arch tokens, preference override, and Importer interface metadata.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add stablediffusion-ggml importer
Detects GGUF-packed Stable Diffusion and FLUX checkpoints (leejet owner,
city96 FLUX mirrors, second-state SD dumps, raw .gguf URLs with arch
tokens) and routes them to the stablediffusion-ggml backend. Registered
BEFORE LlamaCPPImporter so .gguf image checkpoints are not stolen by
llama-cpp's generic .gguf match. Reuses HFOwnerRepoFromURI for the
hfapi-recursion-bug fallback. preferences.backend overrides detection.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for ace-step importer
Covers HF repo-name detection (ACE-Step/ACE-Step-v1-3.5B), preference
override, and Importer interface metadata.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add ace-step importer
Routes ACE-Step music generation checkpoints (ACE-Step/ACE-Step-v1-3.5B,
ACE-Step/Ace-Step1.5, community mirrors) to the ace-step backend.
Matching is case-insensitive on the "ace-step" repo-name substring and
owner, with an HFOwnerRepoFromURI fallback for the hfapi recursion bug.
KnownUsecaseStrings mirrors the gallery's ace-step-turbo entry
(sound_generation, tts). preferences.backend overrides.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): surface ErrAmbiguousImport on text-to-image misses
Adds text-to-image to ambiguousModalities whitelist and covers the
h94/IP-Adapter-FaceID case — pipeline_tag=text-to-image but ships only
.bin/.safetensors so diffusers, stablediffusion-ggml, llama-cpp,
transformers, vllm, mlx, and ace-step all miss. DiscoverModelConfig now
surfaces ErrAmbiguousImport for that shape instead of the opaque
"no importer matched" error.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for vllm-omni importer
Introduces the test surface for the forthcoming VLLMOmniImporter:
detection via preferences.backend, Qwen owner + Omni repo token,
URI-only fallback, negative cases (plain Qwen, random OmniX repo), and
Import() emitting backend: vllm-omni with chat + multimodal usecases.
Includes a registration-order assertion via DiscoverModelConfig to pin
the requirement that vllm-omni wins over vllm for Qwen Omni repos
(tokenizer files are usually present too).
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add vllm-omni importer
Adds VLLMOmniImporter for Qwen Omni-style multimodal checkpoints
(Qwen3-Omni, Qwen2.5-Omni, …). Detection is narrow: HF owner "Qwen"
combined with "omni" in the repo name, or a repo name matching the
-Omni-/Omni- naming pattern. preferences.backend="vllm-omni" always
wins; HFOwnerRepoFromURI provides a URI-only fallback for the hfapi
recursion-bug edge case.
Emitted YAML sets backend: vllm-omni and known_usecases: [chat,
multimodal], matching the gallery/index.yaml vllm-omni entries. The
importer is registered ahead of VLLMImporter so Qwen Omni repos —
which also carry tokenizer files — route to vllm-omni rather than the
plain vllm backend.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for llama-cpp drop-in preferences
Pins the expected drop-in replacement behaviour: preferences.backend
of ik-llama-cpp or turboquant must swap the emitted YAML backend
field while keeping the llama-cpp file layout identical. Also covers
the unknown-backend case (must stay llama-cpp) and re-asserts
AdditionalBackends() returns the two curated entries with non-empty
descriptions.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): llama-cpp honours ik-llama-cpp and turboquant drop-in preferences
preferences.backend set to ik-llama-cpp or turboquant now swaps the
emitted YAML backend field while leaving the file layout, model path,
mmproj handling and everything else in the llama-cpp Import pipeline
untouched. Unknown values are ignored and fall back to backend:
llama-cpp so arbitrary input can't leak into the config.
Aligns the AdditionalBackends() descriptions with the user-facing
naming conventions surfaced via /backends/known. No changes to the
pref-only curated list in endpoints/localai/backend.go: the two
drop-in names have always lived on the importer side via
AdditionalBackends.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for silero-vad importer
Add the SileroVADImporter test fixtures covering metadata, preference
overrides, snakers4 + onnx detection, silero_vad.onnx canonical filename,
URI fallback, and live HF discovery. Implementation follows in the next
commit.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add silero-vad importer
Recognise the Silero VAD ONNX packaging: the canonical silero_vad.onnx
filename or any ONNX file under the snakers4 owner. Emits a
backend: silero-vad config with the vad known_usecase, and attaches the
canonical file entry when present so the weights download on import.
Registered before the generic importers so the unique-filename signal
takes precedence over any downstream tokenizer-based matcher.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for rerankers importer
Cover the RerankersImporter contract: interface metadata, preference
override, cross-encoder owner detection, case-insensitive 'reranker'
substring match (BAAI/bge-reranker, Alibaba-NLP/gte-reranker), URI
fallback, and the full-discovery ordering check that a BAAI reranker
repo must route to the rerankers importer rather than transformers.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add rerankers importer
Recognise reranker repositories — cross-encoder owner or any repo whose
name contains 'reranker' (case-insensitive). Emits backend: rerankers
with reranking: true and the rerank known_usecase.
Registered ahead of sentencetransformers and transformers so reranker
repos that happen to ship tokenizer.json or modules.json still route
here.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for sentencetransformers importer
Cover the SentenceTransformersImporter contract: interface metadata,
preference override, modules.json marker file, sentence_bert_config.json
marker file, sentence-transformers owner, URI fallback, and the
full-discovery ordering check that ensures a sentence-transformers HF
URI routes here rather than transformers.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add sentencetransformers importer
Recognise sentence-transformers embedding repos by modules.json,
sentence_bert_config.json, or the sentence-transformers owner. Emits
backend: sentencetransformers with embeddings: true and the embeddings
known_usecase.
Registered ahead of transformers so ST repos that carry tokenizer.json
still route here.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): add failing tests for rfdetr importer
Cover the RFDetrImporter contract: interface metadata, preference
override, case-insensitive rf-detr and rfdetr substring matches, URI
fallback, and negative cases. Implementation follows in the next
commit.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(gallery/importers): add rfdetr importer
Recognise RF-DETR object-detection repositories by a case-insensitive
'rf-detr' / 'rfdetr' substring in the repo name. Emits backend: rfdetr
with the detection known_usecase.
Registered ahead of transformers so RF-DETR repos with tokenizer
artefacts still route here.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(gallery/importers): surface ErrAmbiguousImport on sentence-similarity misses
Add an ambiguity fixture covering the embeddings/rerankers modality.
Qdrant/bm25 carries pipeline_tag=sentence-similarity but ships only
config.json + stopword .txt files — none of the Batch 5 importers
(silero-vad, rerankers, sentencetransformers, rfdetr) or the generic
vllm/transformers/llama-cpp/mlx/diffusers importers match. Because the
modality is in the ambiguous whitelist, DiscoverModelConfig must
surface ErrAmbiguousImport.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(localai/backend): red tests for KnownBackend.Installed flag
Extend the /backends/known suite with three failing cases that pin down
the forthcoming Installed field: JSON field presence on every entry,
flipping to true when an importer-registered backend is also present on
disk (and staying false for non-installed pref-only entries), and
surfacing system-only backends with empty modality and AutoDetect=false.
A small writeFakeSystemBackend helper plants a run.sh under the backends
dir so gallery.ListSystemBackends recognises the fixture.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(schema,localai/backend): add Installed flag to KnownBackend
Add an Installed bool to schema.KnownBackend and populate it from the
/backends/known handler so the React import form can warn users that
picking a not-yet-installed backend will trigger an automatic download
on submit.
Computation: after merging the importer registry, additional backends
provider entries and the curated pref-only slice, the handler walks
gallery.ListSystemBackends(systemState) and either flips the existing
map entry's Installed flag to true (preserving modality / autodetect /
description metadata) or inserts a bare {Installed:true} entry for
system-only backends the importer layer doesn't know about.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(localai/import_model): structured ambiguous-import response
Add red tests covering the extended ambiguity shape the React import
form needs:
- ImportModelURIEndpoint must return an HTTP 400 body that exposes the
detected `modality` (normalised to the importer modality key, e.g.
"tts" for pipeline_tag=text-to-speech) and a list of `candidates`
(backend names filtered by modality, excluding text-LLM backends).
- The importers package must surface a typed AmbiguousImportError so
HTTP consumers can read Modality + Candidates without parsing the
error string. errors.Is against the existing sentinel keeps working.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(localai/import_model): structured ambiguity response with modality + candidates
DiscoverModelConfig now returns a typed AmbiguousImportError that
carries the importer modality key, candidate backend names, the
original URI, and the raw HF pipeline_tag. Its Is() preserves
errors.Is(err, ErrAmbiguousImport) for legacy callers.
The importer modality is pre-mapped from the HF pipeline_tag
(automatic-speech-recognition → asr, text-to-speech → tts, etc) via
PipelineTagToModality — surfaced as an exported helper so downstream
consumers can avoid duplicating the table. CandidatesForModality
filters the default importer registry plus AdditionalBackendsProvider
drop-ins by modality, sorts deterministically, and is the single
source of truth used by ImportModelURIEndpoint.
ImportModelURIEndpoint now returns HTTP 400 with
{ error, detail, modality, candidates, hint }
when ambiguity fires, letting the React form render a modality-scoped
picker inline instead of a generic toast.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): manual pick badge + tooltip
Red Playwright coverage for the preference-only → manual pick rename:
- The Backend dropdown renders a "manual pick" badge on every option
whose KnownBackend.auto_detect is false.
- The badge carries a title attribute with hover-tooltip copy that
explains auto-detect won't route to this backend.
- Auto-detectable backends must NOT carry the badge.
- The legacy " (preference-only)" suffix is gone from every label.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* ui(import): replace preference-only suffix with manual pick badge
SearchableSelect option rows now support an optional badge field — a
muted pill rendered to the right of the label with an optional title
attribute for native hover tooltips. Plain text so screen readers read
it alongside the option name.
buildBackendOptions in ImportModel stops appending " (preference-only)"
to the label and instead sets badge="manual pick" plus a descriptive
tooltip on every option whose auto_detect is false. The Backend help
text explains what "manual pick" means so users aren't left wondering
about the badge.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): inline ambiguity picker
Red Playwright coverage for Batch A2 — when the server returns a 400
ambiguity body, the form must render an inline alert instead of a
toast, expose one clickable chip per candidate backend, and support
both auto-resubmit on pick and silent dismiss.
- Mocks /api/models/import-uri with the structured ambiguity body
(error, detail, modality, candidates, hint).
- On first click of Import, the alert is visible, carries
modality-specific copy, and shows a chip per candidate.
- Clicking a chip clears the alert, sets the Backend dropdown, and
triggers a second POST to /api/models/import-uri.
- Dismissing the alert leaves the Backend dropdown on Auto-detect —
no implicit backend assignment.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui/import): inline ambiguity alert with candidate chips
Adds AmbiguityAlert — a soft, info-coloured card rendered above the URI
input when the server returns a structured 400 with { modality,
candidates }. Message is modality-aware (tts/asr/embeddings/image/
reranker/detection get purpose-written copy, everything else falls back
to a generic template). Each candidate is a clickable chip that shows a
download icon when /backends/known marks the backend as not yet
installed, so users aren't surprised by an implicit install.
ImportModel wires the alert to handleSimpleImport's error path:
- api.handleResponse now attaches { status, body } to the thrown Error
so pages can pattern-match on structured responses instead of string
error messages.
- handleSimpleImport detects `status === 400 && body.error === 'ambiguous
import'` and flips into the inline-picker mode instead of toasting.
- Clicking a chip sets prefs.backend and auto-resubmits (passing the
picked backend as an override so setPrefs's asynchrony doesn't leak
a stale value).
- Dismissing clears the alert; changing the URI or the backend also
clears it so a stale alert never sticks around.
Test fixtures mock GET /backends/known + POST /models/import-uri so the
Playwright specs don't depend on real network reachability.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): auto-install warning
Red Playwright coverage for Batch A3 — when the user picks a backend
whose KnownBackend.installed is false, the form must render a muted
inline note under the Backend dropdown warning that submitting will
download the backend first. Picking an installed backend or leaving
Auto-detect selected must keep the note hidden.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui/import): auto-install warning under backend dropdown
When the user picks a backend whose KnownBackend.installed is false,
render a muted inline note under the Backend dropdown's help text
warning that submitting will download the backend first. The note
lives inside the same form-group so it lines up with the existing
hint text; it's hidden when Auto-detect is selected (the selected
backend is unknowable at that point) or when the chosen backend is
already on disk.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* ui(import): drop redundant section header, adjust icons, rename HF shortcut
- Remove the "Import from URI" card-level <h2> — the page title already
says "Import New Model" one row up, so the secondary header was
duplicating information.
- Swap the fa-star on "Common Preferences" for fa-sliders (stars imply
favourites/ratings; this is just a preferences block) and move the
Custom Preferences fa-sliders-h to fa-plus-circle so the two blocks
read as distinct rather than as two sliders.
- Rename the HF shortcut from "Search GGUF on HF" → "Browse models on
HF" and drop the `search=gguf` filter on the linked URL. The import
form now supports ~40 backends; hard-coding GGUF in the copy no
longer matches the form's actual reach.
- Pure polish — no behaviour change, covered by the existing Batch A
Playwright suite.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): batch B — simple/power switch, options, tabs, dialog
Adds a failing Playwright suite covering the full Batch B surface ahead
of implementation:
- B1: SimplePowerSwitch segmented control renders, toggles, persists to
localStorage across reloads.
- B2: Simple-mode Options disclosure is collapsed by default; expanding
exposes only Backend, Model Name, Description (no quantizations,
mmproj, model type, or custom prefs).
- B3: Power mode has Preferences and YAML tabs with a persistent
selection across reloads; URI/name/description typed in Simple carry
over to Power; YAML tab swaps the primary action to Create.
- B4: Switching Power -> Simple with a custom preference set triggers
the 3-button confirmation dialog (Keep / Discard / Cancel) with the
documented semantics.
Tests fail against master — implementation lands in the following
commits.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui/import): add SimplePowerSwitch segmented control
Replaces the previous "Advanced Mode / Simple Mode" toggle button in the
page header with a two-segment control that flips between Simple and
Power. The control reuses the existing .segmented CSS shared with the
Sound page for visual consistency.
Mode state is persisted to localStorage under `import-form-mode` so
reloads land on the same view (default: simple). The boolean alias
`isAdvancedMode` is retained internally to minimise diff — subsequent
commits reshape the Simple and Power surfaces independently.
Closes B1 from the Batch B Playwright suite.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui/import): simple mode collapsible options, power tabs, switch dialog
Completes the Batch B surface in a single structural pass so Simple and
Power mode can evolve independently:
Simple mode
- URI input + Ambiguity alert + Import button, plus a collapsible
"Options" disclosure that exposes ONLY Backend, Model Name,
Description. Quantizations / MMProj / Model Type / Diffusers fields
/ Custom Preferences are no longer rendered in Simple mode.
Power mode
- In-page segmented "Preferences · YAML" tab strip. Active tab
persists to localStorage under `import-form-power-tab`.
- Preferences tab = the full existing preferences + custom prefs
panel (no progressive disclosure yet — that's Batch D).
- YAML tab = the existing CodeEditor. Primary button reads "Create"
here, "Import Model" everywhere else.
Switch dialog
- Power -> Simple with non-default prefs (advanced pref keys set,
any custom-pref key non-empty, or YAML edited away from the
template) opens a 3-button dialog: Keep & switch / Discard &
switch / Cancel.
- Keep preserves all state. Discard resets prefs + customPrefs + YAML
to defaults. Cancel leaves the user in Power mode.
Page subtitle reflects the current surface (Simple, Power/Preferences,
Power/YAML). Estimate banner renders everywhere except Power/YAML.
Closes B2/B3/B4 from the Batch B Playwright suite.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): expand Options disclosure in Batch A tests
Batch B hid the Backend dropdown behind a collapsible Options disclosure
in Simple mode. The Batch A tests that exercise the dropdown directly
(manual-pick badge, ambiguity chip sets the selected backend, auto-
install warning) now click the disclosure toggle before asserting on
dropdown contents. Test intent is unchanged.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* ui(import): strip decorative icons from field labels
The preference panel had 12 Font Awesome icons decorating field labels
(Backend, Model Name, Description, Quantizations, MMProj Quantizations,
Model Type, Pipeline Type, Scheduler Type, Enable Parameters, Embeddings,
CUDA, plus fa-link on Model URI). Every label screamed equally, flattening
the visual hierarchy.
Remove them. Keep icons where they carry meaning: page-level section
headers, URI format guide entries, primary buttons, the Simple-mode
Options disclosure, the ambiguity alert's fa-lightbulb, the auto-install
note's fa-download, and the Estimated-requirements banner's
fa-memory / fa-microchip / fa-download.
No new behaviour, no layout / spacing changes beyond removing the
orphaned icon margin. Playwright suite green.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): progressive disclosure of preference fields
Cover the Batch D visibility matrix for Power > Preferences: Quantizations,
MMProj Quantizations, and Model Type each render only for the backends that
can consume them, stay visible when the backend is unset, and preserve any
value the user already typed when toggled off and back on. Also pin the
shrunk Description textarea at rows=2.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui/import): progressive disclosure + shorter description textarea
Gate Quantizations, MMProj Quantizations, and Model Type in the Power >
Preferences tab so each field only renders for the backends that can
actually consume it. Backend unset keeps everything visible. Hidden
fields' state is preserved (the JSX wrapper is guarded, not the
underlying prefs state) so users flipping backends back and forth don't
lose input.
Also shrink the Description textarea from rows=3 to rows=2 — it's
shared between Simple Options and Power Preferences so the change
applies to both.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): enter-to-submit in Simple mode
Red test for Batch F3 — pressing Enter in the URI input must POST
/models/import-uri, and Enter in the Description textarea must insert
a newline without submitting the form.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui/import): enter-to-submit in Simple mode
Wrap the Simple-mode URI input + ambiguity alert + Options disclosure
in a <form> whose onSubmit calls handleSimpleImport. Pressing Enter in
the URI input (or any Simple-mode text input) now submits the import
without having to move the mouse to the header button. The Description
textarea keeps its native behaviour — Enter inserts a newline.
A hidden submit button is included because the visible Import button
lives outside the form in the page header; some browsers only fire
implicit Enter-submit when the form contains a submit-capable element.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* ui(import,SearchableSelect,components): aria-hidden on decorative icons
Every Font Awesome icon in the import form is decorative — its meaning
is already conveyed by adjacent visible text. Adding aria-hidden="true"
prevents screen readers from announcing the unicode glyph point as
content. Covers ImportModel.jsx (all remaining <i> glyphs) and
SearchableSelect.jsx (the trigger chevron).
AmbiguityAlert and SimplePowerSwitch already set aria-hidden on their
icons when the components landed in Batches A and B — no change needed
there.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* ui(SearchableSelect): responsive dropdown maxHeight + hover focus guard
F2 — replace fixed pixel heights with min(pixel, vh) so the dropdown
and its inner scroll region don't overflow short viewports. Outer
container: 260px -> min(260px, 60vh); inner listbox: 200px ->
min(200px, 50vh). Tall viewports still get the original pixel caps.
F5 — short-circuit onMouseEnter when the hovered row is already the
focused row. Avoids queueing a setFocusIndex call (and a render) for
every mousemove inside the same item — the state would be identical.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* ui(import): aria-label on custom preference rows
The Key / Value inputs and trash button in each Custom Preferences row
previously relied on placeholder text alone. Placeholders are not
accessible names — they vanish on input and screen readers do not
announce them consistently. Add row-indexed aria-labels so assistive
tech can distinguish "Preference key for row 1" from "row 2", and give
the trash button an explicit "Remove this preference" label.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* test(ui/import): modality chip row
Red tests for Batch E — a horizontal modality chip row that filters the
Backend dropdown by modality. Covers visibility in Simple-mode Options
and Power/Preferences (and absence in Power/YAML), filter behaviour,
mismatched-backend clearing with toast, ambiguity-alert auto-selection,
and radiogroup keyboard navigation.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* feat(ui/import): add ModalityChips component + filter integration
Horizontal chip row (Any, Text, Speech, TTS, Image, Embeddings,
Rerankers, Detection, VAD) filters the Backend dropdown options to the
selected modality. Default is Any — no filter, current behaviour.
- New ModalityChips component (radiogroup pattern, roving tabindex,
arrow-key navigation, Home/End).
- buildBackendOptions now accepts an optional modalityFilter so grouped
output is narrowed before rendering.
- Chips render inside Simple-mode Options disclosure and Power >
Preferences tab. Power > YAML stays unaffected.
- Switching the filter drops a mismatched backend selection and
surfaces a toast so the auto-clear is visible.
- Ambiguity alerts auto-activate the matching chip so users see only
relevant backends even if they dismiss the alert.
Tightens the Batch E tests' option-matching to the label <span> so the
"↵" keybind hint on the focused row doesn't break accessible-name
lookups.
Assisted-by: Claude:claude-opus-4-7[1m] [Agent]
* fix(ui/import): rename Power to Advanced + stop URI-formats toggle from submitting form
The "Supported URI Formats" disclosure button inside the Simple-mode form
lacked an explicit type attribute, so it defaulted to type="submit". Every
click triggered the form's onSubmit and surfaced the empty-URI validation
toast ("Please enter a model URI"). Marking it type="button" lets it
behave as a pure toggle.
While here, rename the user-visible "Power" label to "Advanced" in the
mode switch (button text + tooltip) and the Power-mode tab's aria-label,
matching the term users actually expect. The internal mode key stays
'power' so tests, localStorage, and data-testid selectors are untouched.
Assisted-by: Claude:claude-opus-4-7
* fix(system): fall back to cpu when meta backend lacks default capability
Meta backends like vllm and sglang enumerate concrete variants for
nvidia/amd/intel/cpu but omit a default: catch-all entry. On a no-GPU
host the reported capability is "default", so the previous Capability()
returned "default" unconditionally on a miss — IsCompatibleWith then saw
no "default" key and filtered the meta out of AvailableBackends. The
import flow's auto-install step then failed with "no backend found with
name <meta>", contradicting the UI's promise that the backend would be
downloaded on demand.
Try the explicit "default" key first, then fall back to "cpu" before
giving up. vllm now resolves to cpu-vllm on CPU-only Linux without
touching the gallery YAML.
Assisted-by: Claude:claude-opus-4-7
|
||
|
Ettore Di Giacinto
|
016da02845 |
feat: refactor shared helpers and enhance MLX backend functionality (#9335)
* refactor(backends): extract python_utils + add mlx_utils shared helpers
Move parse_options() and messages_to_dicts() out of vllm_utils.py into a
new framework-agnostic python_utils.py, and re-export them from vllm_utils
so existing vllm / vllm-omni imports keep working.
Add mlx_utils.py with split_reasoning() and parse_tool_calls() — ported
from mlx_vlm/server.py's process_tool_calls. These work with any
mlx-lm / mlx-vlm tool module (anything exposing tool_call_start,
tool_call_end, parse_tool_call). Used by the mlx and mlx-vlm backends in
later commits to emit structured ChatDelta.tool_calls without
reimplementing per-model parsing.
Shared smoke tests confirm:
- parse_options round-trips bool/int/float/string
- vllm_utils re-exports are identity-equal to python_utils originals
- mlx_utils parse_tool_calls handles <tool_call>...</tool_call> with a
shim module and produces a correctly-indexed list with JSON arguments
- mlx_utils split_reasoning extracts <think> blocks and leaves clean
content
* feat(mlx): wire native tool parsers + ChatDelta + token usage + logprobs
Bring the MLX backend up to the same structured-output contract as vLLM
and llama.cpp: emit Reply.chat_deltas so the OpenAI HTTP layer sees
tool_calls and reasoning_content, not just raw text.
Key insight: mlx_lm.load() returns a TokenizerWrapper that already auto-
detects the right tool parser from the model's chat template
(_infer_tool_parser in mlx_lm/tokenizer_utils.py). The wrapper exposes
has_tool_calling, has_thinking, tool_parser, tool_call_start,
tool_call_end, think_start, think_end — no user configuration needed,
unlike vLLM.
Changes in backend/python/mlx/backend.py:
- Imports: replace inline parse_options / messages_to_dicts with the
shared helpers from python_utils. Pull split_reasoning / parse_tool_calls
from the new mlx_utils shared module.
- LoadModel: log the auto-detected has_tool_calling / has_thinking /
tool_parser_type for observability. Drop the local is_float / is_int
duplicates.
- _prepare_prompt: run request.Messages through messages_to_dicts so
tool_call_id / tool_calls / reasoning_content survive the conversion,
and pass tools=json.loads(request.Tools) + enable_thinking=True (when
request.Metadata says so) to apply_chat_template. Falls back on
TypeError for tokenizers whose template doesn't accept those kwargs.
- _build_generation_params: return an additional (logits_params,
stop_words) pair. Maps RepetitionPenalty / PresencePenalty /
FrequencyPenalty to mlx_lm.sample_utils.make_logits_processors and
threads StopPrompts through to post-decode truncation.
- New _tool_module_from_tokenizer / _finalize_output / _truncate_at_stop
helpers. _finalize_output runs split_reasoning when has_thinking is
true and parse_tool_calls (using a SimpleNamespace shim around the
wrapper's tool_parser callable) when has_tool_calling is true, then
extracts prompt_tokens, generation_tokens and (best-effort) logprobs
from the last GenerationResponse chunk.
- Predict: use make_logits_processors, accumulate text + last_response,
finalize into a structured Reply carrying chat_deltas,
prompt_tokens, tokens, logprobs. Early-stops on user stop sequences.
- PredictStream: per-chunk Reply still carries raw message bytes for
back-compat but now also emits chat_deltas=[ChatDelta(content=delta)].
On loop exit, emit a terminal Reply with structured
reasoning_content / tool_calls / token counts / logprobs — so the Go
side sees tool calls without needing the regex fallback.
- TokenizeString RPC: uses the TokenizerWrapper's encode(); returns
length + tokens or FAILED_PRECONDITION if the model isn't loaded.
- Free RPC: drops model / tokenizer / lru_cache, runs gc.collect(),
calls mx.metal.clear_cache() when available, and best-effort clears
torch.cuda as a belt-and-suspenders.
* feat(mlx-vlm): mirror MLX parity (tool parsers + ChatDelta + samplers)
Same treatment as the MLX backend: emit structured Reply.chat_deltas,
tool_calls, reasoning_content, token counts and logprobs, and extend
sampling parameter coverage beyond the temp/top_p pair the backend
used to handle.
- Imports: drop the inline is_float/is_int helpers, pull parse_options /
messages_to_dicts from python_utils and split_reasoning /
parse_tool_calls from mlx_utils. Also import make_sampler and
make_logits_processors from mlx_lm.sample_utils — mlx-vlm re-uses them.
- LoadModel: use parse_options; call mlx_vlm.tool_parsers._infer_tool_parser
/ load_tool_module to auto-detect a tool module from the processor's
chat_template. Stash think_start / think_end / has_thinking so later
finalisation can split reasoning blocks without duck-typing on each
call. Logs the detected parser type.
- _prepare_prompt: convert proto Messages via messages_to_dicts (so
tool_call_id / tool_calls survive), pass tools=json.loads(request.Tools)
and enable_thinking=True to apply_chat_template when present, fall
back on TypeError for older mlx-vlm versions. Also handle the
prompt-only + media and empty-prompt + media paths consistently.
- _build_generation_params: return (max_tokens, sampler_params,
logits_params, stop_words). Maps repetition_penalty / presence_penalty /
frequency_penalty and passes them through make_logits_processors.
- _finalize_output / _truncate_at_stop: common helper used by Predict
and PredictStream to split reasoning, run parse_tool_calls against the
auto-detected tool module, build ToolCallDelta list, and extract token
counts + logprobs from the last GenerationResult.
- Predict / PredictStream: switch from mlx_vlm.generate to mlx_vlm.stream_generate
in both paths, accumulate text + last_response, pass sampler and
logits_processors through, emit content-only ChatDelta per streaming
chunk followed by a terminal Reply carrying reasoning_content,
tool_calls, prompt_tokens, tokens and logprobs. Non-streaming Predict
returns the same structured Reply shape.
- New helper _collect_media extracted from the duplicated base64 image /
audio decode loop.
- New TokenizeString RPC using the processor's tokenizer.encode and
Free RPC that drops model/processor/config, runs gc + Metal cache
clear + best-effort torch.cuda cache clear.
* feat(importer/mlx): auto-set tool_parser/reasoning_parser on import
Mirror what core/gallery/importers/vllm.go does: after applying the
shared inference defaults, look up the model URI in parser_defaults.json
and append matching tool_parser:/reasoning_parser: entries to Options.
The MLX backends auto-detect tool parsers from the chat template at
runtime so they don't actually consume these options — but surfacing
them in the generated YAML:
- keeps the import experience consistent with vllm
- gives users a single visible place to override
- documents the intended parser for a given model family
* test(mlx): add helper unit tests + TokenizeString/Free + e2e make targets
- backend/python/mlx/test.py: add TestSharedHelpers with server-less
unit tests for parse_options, messages_to_dicts, split_reasoning and
parse_tool_calls (using a SimpleNamespace shim to fake a tool module
without requiring a model). Plus test_tokenize_string and test_free
RPC tests that load a tiny MLX-quantized Llama and exercise the new
RPCs end-to-end.
- backend/python/mlx-vlm/test.py: same helper unit tests + cleanup of
the duplicated import block at the top of the file.
- Makefile: register BACKEND_MLX and BACKEND_MLX_VLM (they were missing
from the docker-build-target eval list — only mlx-distributed had a
generated target before). Add test-extra-backend-mlx and
test-extra-backend-mlx-vlm convenience targets that build the
respective image and run tests/e2e-backends with the tools capability
against mlx-community/Qwen2.5-0.5B-Instruct-4bit. The MLX backend
auto-detects the tool parser from the chat template so no
BACKEND_TEST_OPTIONS is needed (unlike vllm).
* fix(libbackend): don't pass --copies to venv unless PORTABLE_PYTHON=true
backend/python/common/libbackend.sh:ensureVenv() always invoked
'python -m venv --copies', but macOS system python (and some other
builds) refuses with:
Error: This build of python cannot create venvs without using symlinks
--copies only matters when _makeVenvPortable later relocates the venv,
which only happens when PORTABLE_PYTHON=true. Make --copies conditional
on that flag and fall back to default (symlinked) venv otherwise.
Caught while bringing up the mlx backend on Apple Silicon — the same
build path is used by every Python backend with USE_PIP=true.
* fix(mlx): support mlx-lm 0.29.x tool calling + drop deprecated clear_cache
The released mlx-lm 0.29.x ships a much simpler tool-calling API than
HEAD: TokenizerWrapper detects the <tool_call>...</tool_call> markers
from the tokenizer vocab and exposes has_tool_calling /
tool_call_start / tool_call_end, but does NOT expose a tool_parser
callable on the wrapper and does NOT ship a mlx_lm.tool_parsers
subpackage at all (those only exist on main).
Caught while running the smoke test on Apple Silicon with the
released mlx-lm 0.29.1: tokenizer.tool_parser raised AttributeError
(falling through to the underlying HF tokenizer), so
_tool_module_from_tokenizer always returned None and tool calls slipped
through as raw <tool_call>...</tool_call> text in Reply.message instead
of being parsed into ChatDelta.tool_calls.
Fix: when has_tool_calling is True but tokenizer.tool_parser is missing,
default the parse_tool_call callable to json.loads(body.strip()) — that's
exactly what mlx_lm.tool_parsers.json_tools.parse_tool_call does on HEAD
and covers the only format 0.29 detects (<tool_call>JSON</tool_call>).
Future mlx-lm releases that ship more parsers will be picked up
automatically via the tokenizer.tool_parser attribute when present.
Also tighten the LoadModel logging — the old log line read
init_kwargs.get('tool_parser_type') which doesn't exist on 0.29 and
showed None even when has_tool_calling was True. Log the actual
tool_call_start / tool_call_end markers instead.
While here, switch Free()'s Metal cache clear from the deprecated
mx.metal.clear_cache to mx.clear_cache (mlx >= 0.30), with a
fallback for older releases. Mirrored to the mlx-vlm backend.
* feat(mlx-distributed): mirror MLX parity (tool calls + ChatDelta + sampler)
Same treatment as the mlx and mlx-vlm backends: emit Reply.chat_deltas
with structured tool_calls / reasoning_content / token counts /
logprobs, expand sampling parameter coverage beyond temp+top_p, and
add the missing TokenizeString and Free RPCs.
Notes specific to mlx-distributed:
- Rank 0 is the only rank that owns a sampler — workers participate in
the pipeline-parallel forward pass via mx.distributed and don't
re-implement sampling. So the new logits_params (repetition_penalty,
presence_penalty, frequency_penalty) and stop_words apply on rank 0
only; we don't need to extend coordinator.broadcast_generation_params,
which still ships only max_tokens / temperature / top_p to workers
(everything else is a rank-0 concern).
- Free() now broadcasts CMD_SHUTDOWN to workers when a coordinator is
active, so they release the model on their end too. The constant is
already defined and handled by the existing worker loop in
backend.py:633 (CMD_SHUTDOWN = -1).
- Drop the locally-defined is_float / is_int / parse_options trio in
favor of python_utils.parse_options, re-exported under the module
name for back-compat with anything that imported it directly.
- _prepare_prompt: route through messages_to_dicts so tool_call_id /
tool_calls / reasoning_content survive, pass tools=json.loads(
request.Tools) and enable_thinking=True to apply_chat_template, fall
back on TypeError for templates that don't accept those kwargs.
- New _tool_module_from_tokenizer (with the json.loads fallback for
mlx-lm 0.29.x), _finalize_output, _truncate_at_stop helpers — same
contract as the mlx backend.
- LoadModel logs the auto-detected has_tool_calling / has_thinking /
tool_call_start / tool_call_end so users can see what the wrapper
picked up for the loaded model.
- backend/python/mlx-distributed/test.py: add the same TestSharedHelpers
unit tests (parse_options, messages_to_dicts, split_reasoning,
parse_tool_calls) that exist for mlx and mlx-vlm.
|
||
|
Ettore Di Giacinto
|
d67623230f |
feat(vllm): parity with llama.cpp backend (#9328)
* fix(schema): serialize ToolCallID and Reasoning in Messages.ToProto
The ToProto conversion was dropping tool_call_id and reasoning_content
even though both proto and Go fields existed, breaking multi-turn tool
calling and reasoning passthrough to backends.
* refactor(config): introduce backend hook system and migrate llama-cpp defaults
Adds RegisterBackendHook/runBackendHooks so each backend can register
default-filling functions that run during ModelConfig.SetDefaults().
Migrates the existing GGUF guessing logic into hooks_llamacpp.go,
registered for both 'llama-cpp' and the empty backend (auto-detect).
Removes the old guesser.go shim.
* feat(config): add vLLM parser defaults hook and importer auto-detection
Introduces parser_defaults.json mapping model families to vLLM
tool_parser/reasoning_parser names, with longest-pattern-first matching.
The vllmDefaults hook auto-fills tool_parser and reasoning_parser
options at load time for known families, while the VLLMImporter writes
the same values into generated YAML so users can review and edit them.
Adds tests covering MatchParserDefaults, hook registration via
SetDefaults, and the user-override behavior.
* feat(vllm): wire native tool/reasoning parsers + chat deltas + logprobs
- Use vLLM's ToolParserManager/ReasoningParserManager to extract structured
output (tool calls, reasoning content) instead of reimplementing parsing
- Convert proto Messages to dicts and pass tools to apply_chat_template
- Emit ChatDelta with content/reasoning_content/tool_calls in Reply
- Extract prompt_tokens, completion_tokens, and logprobs from output
- Replace boolean GuidedDecoding with proper GuidedDecodingParams from Grammar
- Add TokenizeString and Free RPC methods
- Fix missing `time` import used by load_video()
* feat(vllm): CPU support + shared utils + vllm-omni feature parity
- Split vllm install per acceleration: move generic `vllm` out of
requirements-after.txt into per-profile after files (cublas12, hipblas,
intel) and add CPU wheel URL for cpu-after.txt
- requirements-cpu.txt now pulls torch==2.7.0+cpu from PyTorch CPU index
- backend/index.yaml: register cpu-vllm / cpu-vllm-development variants
- New backend/python/common/vllm_utils.py: shared parse_options,
messages_to_dicts, setup_parsers helpers (used by both vllm backends)
- vllm-omni: replace hardcoded chat template with tokenizer.apply_chat_template,
wire native parsers via shared utils, emit ChatDelta with token counts,
add TokenizeString and Free RPCs, detect CPU and set VLLM_TARGET_DEVICE
- Add test_cpu_inference.py: standalone script to validate CPU build with
a small model (Qwen2.5-0.5B-Instruct)
* fix(vllm): CPU build compatibility with vllm 0.14.1
Validated end-to-end on CPU with Qwen2.5-0.5B-Instruct (LoadModel, Predict,
TokenizeString, Free all working).
- requirements-cpu-after.txt: pin vllm to 0.14.1+cpu (pre-built wheel from
GitHub releases) for x86_64 and aarch64. vllm 0.14.1 is the newest CPU
wheel whose torch dependency resolves against published PyTorch builds
(torch==2.9.1+cpu). Later vllm CPU wheels currently require
torch==2.10.0+cpu which is only available on the PyTorch test channel
with incompatible torchvision.
- requirements-cpu.txt: bump torch to 2.9.1+cpu, add torchvision/torchaudio
so uv resolves them consistently from the PyTorch CPU index.
- install.sh: add --index-strategy=unsafe-best-match for CPU builds so uv
can mix the PyTorch index and PyPI for transitive deps (matches the
existing intel profile behaviour).
- backend.py LoadModel: vllm >= 0.14 removed AsyncLLMEngine.get_model_config
so the old code path errored out with AttributeError on model load.
Switch to the new get_tokenizer()/tokenizer accessor with a fallback
to building the tokenizer directly from request.Model.
* fix(vllm): tool parser constructor compat + e2e tool calling test
Concrete vLLM tool parsers override the abstract base's __init__ and
drop the tools kwarg (e.g. Hermes2ProToolParser only takes tokenizer).
Instantiating with tools= raised TypeError which was silently caught,
leaving chat_deltas.tool_calls empty.
Retry the constructor without the tools kwarg on TypeError — tools
aren't required by these parsers since extract_tool_calls finds tool
syntax in the raw model output directly.
Validated with Qwen/Qwen2.5-0.5B-Instruct + hermes parser on CPU:
the backend correctly returns ToolCallDelta{name='get_weather',
arguments='{"location": "Paris, France"}'} in ChatDelta.
test_tool_calls.py is a standalone smoke test that spawns the gRPC
backend, sends a chat completion with tools, and asserts the response
contains a structured tool call.
* ci(backend): build cpu-vllm container image
Add the cpu-vllm variant to the backend container build matrix so the
image registered in backend/index.yaml (cpu-vllm / cpu-vllm-development)
is actually produced by CI.
Follows the same pattern as the other CPU python backends
(cpu-diffusers, cpu-chatterbox, etc.) with build-type='' and no CUDA.
backend_pr.yml auto-picks this up via its matrix filter from backend.yml.
* test(e2e-backends): add tools capability + HF model name support
Extends tests/e2e-backends to cover backends that:
- Resolve HuggingFace model ids natively (vllm, vllm-omni) instead of
loading a local file: BACKEND_TEST_MODEL_NAME is passed verbatim as
ModelOptions.Model with no download/ModelFile.
- Parse tool calls into ChatDelta.tool_calls: new "tools" capability
sends a Predict with a get_weather function definition and asserts
the Reply contains a matching ToolCallDelta. Uses UseTokenizerTemplate
with OpenAI-style Messages so the backend can wire tools into the
model's chat template.
- Need backend-specific Options[]: BACKEND_TEST_OPTIONS lets a test set
e.g. "tool_parser:hermes,reasoning_parser:qwen3" at LoadModel time.
Adds make target test-extra-backend-vllm that:
- docker-build-vllm
- loads Qwen/Qwen2.5-0.5B-Instruct
- runs health,load,predict,stream,tools with tool_parser:hermes
Drops backend/python/vllm/test_{cpu_inference,tool_calls}.py — those
standalone scripts were scaffolding used while bringing up the Python
backend; the e2e-backends harness now covers the same ground uniformly
alongside llama-cpp and ik-llama-cpp.
* ci(test-extra): run vllm e2e tests on CPU
Adds tests-vllm-grpc to the test-extra workflow, mirroring the
llama-cpp and ik-llama-cpp gRPC jobs. Triggers when files under
backend/python/vllm/ change (or on run-all), builds the local-ai
vllm container image, and runs the tests/e2e-backends harness with
BACKEND_TEST_MODEL_NAME=Qwen/Qwen2.5-0.5B-Instruct, tool_parser:hermes,
and the tools capability enabled.
Uses ubuntu-latest (no GPU) — vllm runs on CPU via the cpu-vllm
wheel we pinned in requirements-cpu-after.txt. Frees disk space
before the build since the docker image + torch + vllm wheel is
sizeable.
* fix(vllm): build from source on CI to avoid SIGILL on prebuilt wheel
The prebuilt vllm 0.14.1+cpu wheel from GitHub releases is compiled with
SIMD instructions (AVX-512 VNNI/BF16 or AMX-BF16) that not every CPU
supports. GitHub Actions ubuntu-latest runners SIGILL when vllm spawns
the model_executor.models.registry subprocess for introspection, so
LoadModel never reaches the actual inference path.
- install.sh: when FROM_SOURCE=true on a CPU build, temporarily hide
requirements-cpu-after.txt so installRequirements installs the base
deps + torch CPU without pulling the prebuilt wheel, then clone vllm
and compile it with VLLM_TARGET_DEVICE=cpu. The resulting binaries
target the host's actual CPU.
- backend/Dockerfile.python: accept a FROM_SOURCE build-arg and expose
it as an ENV so install.sh sees it during `make`.
- Makefile docker-build-backend: forward FROM_SOURCE as --build-arg
when set, so backends that need source builds can opt in.
- Makefile test-extra-backend-vllm: call docker-build-vllm via a
recursive $(MAKE) invocation so FROM_SOURCE flows through.
- .github/workflows/test-extra.yml: set FROM_SOURCE=true on the
tests-vllm-grpc job. Slower but reliable — the prebuilt wheel only
works on hosts that share the build-time SIMD baseline.
Answers 'did you test locally?': yes, end-to-end on my local machine
with the prebuilt wheel (CPU supports AVX-512 VNNI). The CI runner CPU
gap was not covered locally — this commit plugs that gap.
* ci(vllm): use bigger-runner instead of source build
The prebuilt vllm 0.14.1+cpu wheel requires SIMD instructions (AVX-512
VNNI/BF16) that stock ubuntu-latest GitHub runners don't support —
vllm.model_executor.models.registry SIGILLs on import during LoadModel.
Source compilation works but takes 30-40 minutes per CI run, which is
too slow for an e2e smoke test. Instead, switch tests-vllm-grpc to the
bigger-runner self-hosted label (already used by backend.yml for the
llama-cpp CUDA build) — that hardware has the required SIMD baseline
and the prebuilt wheel runs cleanly.
FROM_SOURCE=true is kept as an opt-in escape hatch:
- install.sh still has the CPU source-build path for hosts that need it
- backend/Dockerfile.python still declares the ARG + ENV
- Makefile docker-build-backend still forwards the build-arg when set
Default CI path uses the fast prebuilt wheel; source build can be
re-enabled by exporting FROM_SOURCE=true in the environment.
* ci(vllm): install make + build deps on bigger-runner
bigger-runner is a bare self-hosted runner used by backend.yml for
docker image builds — it has docker but not the usual ubuntu-latest
toolchain. The make-based test target needs make, build-essential
(cgo in 'go test'), and curl/unzip (the Makefile protoc target
downloads protoc from github releases).
protoc-gen-go and protoc-gen-go-grpc come via 'go install' in the
install-go-tools target, which setup-go makes possible.
* ci(vllm): install libnuma1 + libgomp1 on bigger-runner
The vllm 0.14.1+cpu wheel ships a _C C++ extension that dlopens
libnuma.so.1 at import time. When the runner host doesn't have it,
the extension silently fails to register its torch ops, so
EngineCore crashes on init_device with:
AttributeError: '_OpNamespace' '_C_utils' object has no attribute
'init_cpu_threads_env'
Also add libgomp1 (OpenMP runtime, used by torch CPU kernels) to be
safe on stripped-down runners.
* feat(vllm): bundle libnuma/libgomp via package.sh
The vllm CPU wheel ships a _C extension that dlopens libnuma.so.1 at
import time; torch's CPU kernels in turn use libgomp.so.1 (OpenMP).
Without these on the host, vllm._C silently fails to register its
torch ops and EngineCore crashes with:
AttributeError: '_OpNamespace' '_C_utils' object has no attribute
'init_cpu_threads_env'
Rather than asking every user to install libnuma1/libgomp1 on their
host (or every LocalAI base image to ship them), bundle them into
the backend image itself — same pattern fish-speech and the GPU libs
already use. libbackend.sh adds ${EDIR}/lib to LD_LIBRARY_PATH at
run time so the bundled copies are picked up automatically.
- backend/python/vllm/package.sh (new): copies libnuma.so.1 and
libgomp.so.1 from the builder's multilib paths into ${BACKEND}/lib,
preserving soname symlinks. Runs during Dockerfile.python's
'Run backend-specific packaging' step (which already invokes
package.sh if present).
- backend/Dockerfile.python: install libnuma1 + libgomp1 in the
builder stage so package.sh has something to copy (the Ubuntu
base image otherwise only has libgomp in the gcc dep chain).
- test-extra.yml: drop the workaround that installed these libs on
the runner host — with the backend image self-contained, the
runner no longer needs them, and the test now exercises the
packaging path end-to-end the way a production host would.
* ci(vllm): disable tests-vllm-grpc job (heterogeneous runners)
Both ubuntu-latest and bigger-runner have inconsistent CPU baselines:
some instances support the AVX-512 VNNI/BF16 instructions the prebuilt
vllm 0.14.1+cpu wheel was compiled with, others SIGILL on import of
vllm.model_executor.models.registry. The libnuma packaging fix doesn't
help when the wheel itself can't be loaded.
FROM_SOURCE=true compiles vllm against the actual host CPU and works
everywhere, but takes 30-50 minutes per run — too slow for a smoke
test on every PR.
Comment out the job for now. The test itself is intact and passes
locally; run it via 'make test-extra-backend-vllm' on a host with the
required SIMD baseline. Re-enable when:
- we have a self-hosted runner label with guaranteed AVX-512 VNNI/BF16, or
- vllm publishes a CPU wheel with a wider baseline, or
- we set up a docker layer cache that makes FROM_SOURCE acceptable
The detect-changes vllm output, the test harness changes (tests/
e2e-backends + tools cap), the make target (test-extra-backend-vllm),
the package.sh and the Dockerfile/install.sh plumbing all stay in
place.
|
||
|
Ettore Di Giacinto
|
59108fbe32 |
feat: add distributed mode (#9124)
* feat: add distributed mode (experimental) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix data races, mutexes, transactions Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactorings Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix events and tool stream in agent chat Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * use ginkgo Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(cron): compute correctly time boundaries avoiding re-triggering Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * enhancements, refactorings Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * do not flood of healthy checks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * do not list obvious backends as text backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * tests fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring and consolidation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop redundant healthcheck Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * enhancements, refactorings Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
031a36c995 |
feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092)
* feat: wire min_p Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: inferencing defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(refactor): re-use iterative parser Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore: generate automatically inference defaults from unsloth Instead of trying to re-invent the wheel and maintain here the inference defaults, prefer to consume unsloth ones, and contribute there as necessary. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore: apply defaults also to models installed via gallery Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore: be consistent and apply fallback to all endpoint Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
d9c1db2b87 |
feat: add (experimental) fine-tuning support with TRL (#9088)
* feat: add fine-tuning endpoint Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(experimental): add fine-tuning endpoint and TRL support This changeset defines new GRPC signatues for Fine tuning backends, and add TRL backend as initial fine-tuning engine. This implementation also supports exporting to GGUF and automatically importing it to LocalAI after fine-tuning. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * commit TRL backend, stop by killing process Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * move fine-tune to generic features Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add evals, reorder menu Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
LocalAI [bot]
|
bf4f8da266 |
fix: include model name in mmproj file path to prevent model isolation (#8937) (#8940)
* fix: include model name in mmproj file path to prevent model isolation issues This fix addresses issue #8937 where different models with mmproj files having the same filename (e.g., mmproj-F32.gguf) would overwrite each other. By including the model name in the path (llama-cpp/mmproj/<model-name>/<filename>), each model's mmproj files are now stored in separate directories, preventing the collision that caused conversations to fail when switching between models. Fixes #8937 Signed-off-by: LocalAI Bot <localai-bot@example.com> * test: update test expectations for model name in mmproj path The test file had hardcoded expectations for the old mmproj path format. Updated the test expectations to include the model name subdirectory to match the new path structure introduced in the fix. Fixes CI failures on tests-apple and tests-linux * fix: add model name to model path for consistency with mmproj path This change makes the model path consistent with the mmproj path by including the model name subdirectory in both paths: - mmproj: llama-cpp/mmproj/<model-name>/<filename> - model: llama-cpp/models/<model-name>/<filename> This addresses the reviewer's feedback that the model config generation needs to correctly reference the mmproj file path. Fixes the issue where the model path didn't include the model name subdirectory while the mmproj path did. Signed-off-by: team-coding-agent-1 <team-coding-agent-1@localai.dev> --------- Signed-off-by: LocalAI Bot <localai-bot@example.com> Signed-off-by: team-coding-agent-1 <team-coding-agent-1@localai.dev> Co-authored-by: team-coding-agent-1 <team-coding-agent-1@localai.dev> |
||
|
Ettore Di Giacinto
|
c37785b78c |
chore(refactor): move logging to common package based on slog (#7668)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
8ca98c90ea |
chore(importers/llama.cpp): add models to 'llama-cpp' subfolder (#7450)
This makes paths predictable, and avoids multiple model files to show in the main view Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Copilot
|
16e5689162 |
feat(importers): Add diffuser backend importer with ginkgo tests and UI support (#7316)
* Initial plan * Add diffuser backend importer with ginkgo tests Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> * Finalize diffuser backend importer implementation Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> * Add diffuser preferences to model-editor import section Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> * Use gopkg.in/yaml.v3 for consistency in diffuser importer Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> |
||
|
Ettore Di Giacinto
|
77bbeed57e |
feat(importer): unify importing code with CLI (#7299)
* feat(importer): support ollama and OCI, unify code Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: support importing from local file Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * support also yaml config files Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Correctly handle local files Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Extract importing errors Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add importer tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add integration tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(UX): improve and specify supported URI formats Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fail if backend does not have a runfile Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(gallery): add cache for galleries Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(ui): remove handler duplicate File input handlers are now handled by Alpine.js @change handlers in chat.html. Removed duplicate listeners to prevent files from being processed twice Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(ui): be consistent in attachments in the chat Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fail if no importer matches Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: propagate ops correctly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
be8cf838c2 |
feat(importers): add transformers and vLLM (#7278)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
b1d1f2a37d |
chore(importers): small logic enhancements (#7262)
* chore(import): import mmproj files to specific folder Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Slightly enhance logics Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |
||
|
Ettore Di Giacinto
|
3728552e94 |
feat: import models via URI (#7245)
* feat: initial hook to install elements directly Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * WIP: ui changes Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move HF api client to pkg Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add simple importer for gguf files Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add opcache Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wire importers to CLI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add omitempty to config fields Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add MLX importer Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small refactors to star to use HF for discovery Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Common preferences Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add support to bare HF repos Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(importer/llama.cpp): add support for mmproj files Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add mmproj quants to common preferences Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix vlm usage in tokenizer mode with llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> |