* feat(backend): add turboquant llama.cpp-fork backend
turboquant is a llama.cpp fork (TheTom/llama-cpp-turboquant, branch
feature/turboquant-kv-cache) that adds a TurboQuant KV-cache scheme.
It ships as a first-class backend reusing backend/cpp/llama-cpp sources
via a thin wrapper Makefile: each variant target copies ../llama-cpp
into a sibling build dir and invokes llama-cpp's build-llama-cpp-grpc-server
with LLAMA_REPO/LLAMA_VERSION overridden to point at the fork. No
duplication of grpc-server.cpp — upstream fixes flow through automatically.
Wires up the full matrix (CPU, CUDA 12/13, L4T, L4T-CUDA13, ROCm, SYCL
f32/f16, Vulkan) in backend.yml and the gallery entries in index.yaml,
adds a tests-turboquant-grpc e2e job driven by BACKEND_TEST_CACHE_TYPE_K/V=q8_0
to exercise the KV-cache config path (backend_test.go gains dedicated env
vars wired into ModelOptions.CacheTypeKey/Value — a generic improvement
usable by any llama.cpp-family backend), and registers a nightly auto-bump
PR in bump_deps.yaml tracking feature/turboquant-kv-cache.
scripts/changed-backends.js gets a special-case so edits to
backend/cpp/llama-cpp/ also retrigger the turboquant CI pipeline, since
the wrapper reuses those sources.
* feat(turboquant): carry upstream patches against fork API drift
turboquant branched from llama.cpp before upstream commit 66060008
("server: respect the ignore eos flag", #21203) which added the
`logit_bias_eog` field to `server_context_meta` and a matching
parameter to `server_task::params_from_json_cmpl`. The shared
backend/cpp/llama-cpp/grpc-server.cpp depends on that field, so
building it against the fork unmodified fails.
Cherry-pick that commit as a patch file under
backend/cpp/turboquant/patches/ and apply it to the cloned fork
sources via a new apply-patches.sh hook called from the wrapper
Makefile. Simplifies the build flow too: instead of hopping through
llama-cpp's build-llama-cpp-grpc-server indirection, the wrapper now
drives the copied Makefile directly (clone -> patch -> build).
Drop the corresponding patch whenever the fork catches up with
upstream — the build fails fast if a patch stops applying, which
is the signal to retire it.
* docs: add turboquant backend section + clarify cache_type_k/v
Document the new turboquant (llama.cpp fork with TurboQuant KV-cache)
backend alongside the existing llama-cpp / ik-llama-cpp sections in
features/text-generation.md: when to pick it, how to install it from
the gallery, and a YAML example showing backend: turboquant together
with cache_type_k / cache_type_v.
Also expand the cache_type_k / cache_type_v table rows in
advanced/model-configuration.md to spell out the accepted llama.cpp
quantization values and note that these fields apply to all
llama.cpp-family backends, not just vLLM.
* feat(turboquant): patch ggml-rpc GGML_OP_COUNT assertion
The fork adds new GGML ops bringing GGML_OP_COUNT to 97, but
ggml/include/ggml-rpc.h static-asserts it equals 96, breaking
the GGML_RPC=ON build paths (turboquant-grpc / turboquant-rpc-server).
Carry a one-line patch that updates the expected count so the
assertion holds. Drop this patch whenever the fork fixes it upstream.
* feat(turboquant): allow turbo* KV-cache types and exercise them in e2e
The shared backend/cpp/llama-cpp/grpc-server.cpp carries its own
allow-list of accepted KV-cache types (kv_cache_types[]) and rejects
anything outside it before the value reaches llama.cpp's parser. That
list only contains the standard llama.cpp types — turbo2/turbo3/turbo4
would throw "Unsupported cache type" at LoadModel time, meaning
nothing the LocalAI gRPC layer accepted was actually fork-specific.
Add a build-time augmentation step (patch-grpc-server.sh, called from
the turboquant wrapper Makefile) that inserts GGML_TYPE_TURBO2_0/3_0/4_0
into the allow-list of the *copied* grpc-server.cpp under
turboquant-<flavor>-build/. The original file under backend/cpp/llama-cpp/
is never touched, so the stock llama-cpp build keeps compiling against
vanilla upstream which has no notion of those enum values.
Switch test-extra-backend-turboquant to set
BACKEND_TEST_CACHE_TYPE_K=turbo3 / _V=turbo3 so the e2e gRPC suite
actually runs the fork's TurboQuant KV-cache code paths (turbo3 also
auto-enables flash_attention in the fork). Picking q8_0 here would
only re-test the standard llama.cpp path that the upstream llama-cpp
backend already covers.
Refresh the docs (text-generation.md + model-configuration.md) to
list turbo2/turbo3/turbo4 explicitly and call out that you only get
the TurboQuant code path with this backend + a turbo* cache type.
* fix(turboquant): rewrite patch-grpc-server.sh in awk, not python3
The builder image (ubuntu:24.04 stage-2 in Dockerfile.turboquant)
does not install python3, so the python-based augmentation step
errored with `python3: command not found` at make time. Switch to
awk, which ships in coreutils and is already available everywhere
the rest of the wrapper Makefile runs.
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
openai-functions.md used to claim LocalAI tool calling worked only on
llama.cpp-compatible models. That was true when it was written; it's
not true now — vLLM (since PR #9328) and MLX/MLX-VLM both extract
structured tool calls from model output.
- openai-functions.md: new 'Supported backends' matrix covering
llama.cpp, vllm, vllm-omni, mlx, mlx-vlm, with the key distinction
that vllm needs an explicit tool_parser: option while mlx auto-
detects from the chat template. Reasoning content (think tags) is
extracted on the same set of backends. Added setup snippets for
both the vllm and mlx paths, and noted the gallery importer
pre-fills tool_parser:/reasoning_parser: for known families.
- compatibility-table.md: fix the stale 'Streaming: no' for vllm,
vllm-omni, mlx, mlx-vlm (all four support streaming now). Add
'Functions' to their capabilities. Also widen the MLX Acceleration
column to reflect the CPU/CUDA/Jetson L4T backends that already
exist in backend/index.yaml — 'Metal' on its own was misleading.
* always enable parallel requests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: add node reconciler, allow to schedule to group of nodes, min/max autoscaler
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: move tests to ginkgo
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(smart router): order by available vram
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* 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>
* 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>
* feat(ui): add users and authentication support
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: allow the admin user to impersonificate users
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: ui improvements, disable 'Users' button in navbar when no auth is configured
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: add OIDC support
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: gate models
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: cache requests to optimize speed
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* small UI enhancements
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(ui): style improvements
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: cover other paths by auth
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: separate local auth, refactor
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* security hardening, approval mode
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: fix tests and expectations
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: update localagi/localrecall
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
docs: Add troubleshooting guide for embedding models (#9064)
- Add section on using gallery models for embeddings
- Document common issues with embedding model configuration
- Add troubleshooting guide for Qwen3 embedding models
- Include correct configuration examples for Qwen3-Embedding-4B
- Document context size limits and dimension parameters
- Add table of Qwen3 embedding model specifications
Fixes#9064
Signed-off-by: localai-bot <localai-bot@localai.io>
Co-authored-by: localai-bot <localai-bot@localai.io>
AIO images are behind, and takes effort to maintain these. Wizard and
installation of models have been semplified massively, so AIO images
lost their purpose.
This allows us to be more laser focused on main images and reliefes
stress from CI.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(realtime): WebRTC support
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(tracing): Show full LLM opts and deltas
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(mlx-distributed): add new MLX-distributed backend
Add new MLX distributed backend with support for both TCP and RDMA for
model sharding.
This implementation ties in the discovery implementation already in
place, and re-uses the same P2P mechanism for the TCP MLX-distributed
inferencing.
The Auto-parallel implementation is inspired by Exo's
ones (who have been added to acknowledgement for the great work!)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* expose a CLI to facilitate backend starting
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: make manual rank0 configurable via model configs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add missing features from mlx backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
feat: add --data-path CLI flag for persistent data separation
- Add LOCALAI_DATA_PATH environment variable and --data-path CLI flag
- Default data path: /data (separate from configuration directory)
- Automatic migration on startup: moves agent_tasks.json, agent_jobs.json, collections/, and assets/ from old config dir to new data path
- Backward compatible: preserves old behavior if LOCALAI_DATA_PATH is not set
- Agent state and job directories now use DataPath with proper fallback chain
- Update documentation with new flag and docker-compose example
This separates mutable persistent data (collectiondb, agents, assets, skills) from configuration files, enabling better volume mounting and data persistence in containerized deployments.
Signed-off-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
* feat: add documentation for undocumented API endpoints
Creates comprehensive documentation for 8 previously undocumented endpoints:
- Voice Activity Detection (/v1/vad)
- Video Generation (/video)
- Sound Generation (/v1/sound-generation)
- Backend Monitor (/backend/monitor, /backend/shutdown)
- Token Metrics (/tokenMetrics)
- P2P endpoints (/api/p2p/* - 5 sub-endpoints)
- System Info (/system, /version)
Each documentation file includes HTTP method, request/response schemas,
curl examples, sample JSON responses, and error codes.
* docs: remove token-metrics endpoint documentation per review feedback
The token-metrics endpoint is not wired into the HTTP router and
should not be documented per reviewer request.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: move system-info documentation to reference section
Per review feedback, system-info endpoint docs are better suited
for the reference section rather than features.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
feat: add shell completion support for bash, zsh, and fish
- Add core/cli/completion.go with dynamic completion script generation
- Add core/cli/completion_test.go with unit tests
- Modify cmd/local-ai/main.go to support completion command
- Modify core/cli/cli.go to add Completion subcommand
- Add docs/content/features/shell-completion.md with installation instructions
The completion scripts are generated dynamically from the Kong CLI model,
so they automatically include all commands, subcommands, and flags.
Co-authored-by: localai-bot <localai-bot@noreply.github.com>
* feat: add standalone and agentic functionalities
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* expose agents via responses api
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: Add LOCALAI_DISABLE_MCP environment variable to disable MCP support
- Added DisableMCP field to RunCMD struct in core/cli/run.go
- Added LOCALAI_DISABLE_MCP environment variable support
- Added DisableMCP field to ApplicationConfig struct
- Added DisableMCP AppOption function
- Updated MCP endpoint routing to check appConfig.DisableMCP
- When LOCALAI_DISABLE_MCP is set to true/1/yes, MCP endpoints are not registered
When set, all MCP functionality is disabled and appropriate error messages
are returned to users.
Use Cases:
- Security-conscious deployments where MCP is not needed
- Reducing attack surface
- Compliance requirements that prohibit certain protocol support
Environment variable: LOCALAI_DISABLE_MCP=true
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
* docs: Add documentation for LOCALAI_DISABLE_MCP environment variable
- Add section explaining how to disable MCP support using environment variable
- Document use cases for disabling MCP
- Provide examples for CLI and Docker usage
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
---------
Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
* Add support for multiple voice clones in Qwen TTS
Signed-off-by: Andres Smith <andressmithdev@pm.me>
* Add voice prompt caching and generation logs to see generation time
---------
Signed-off-by: Andres Smith <andressmithdev@pm.me>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* docs: update diffusers multi-GPU documentation to mention tensor_parallel_size configuration
* chore: revert backend/python/diffusers/README.md to original content
---------
Co-authored-by: Your Name <you@example.com>
Fixes#8212 - Updated the note about reporting broken models to
reference the main LocalAI repository instead of the outdated
separate gallery repository reference.
* feat(musicgen): add ace-step and UI interface
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Correctly handle model dir
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Drop auto-download
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add to models, fixup UIs icons
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* l4t13 is incompatbile
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* avoid pinning version for cuda12
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Drop l4t12
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* WIP response format implementation for audio transcriptions
(cherry picked from commit e271dd764bbc13846accf3beb8b6522153aa276f)
Signed-off-by: Andres Smith <andressmithdev@pm.me>
* Rework transcript response_format and add more formats
(cherry picked from commit 6a93a8f63e2ee5726bca2980b0c9cf4ef8b7aeb8)
Signed-off-by: Andres Smith <andressmithdev@pm.me>
* Add test and replace go-openai package with official openai go client
(cherry picked from commit f25d1a04e46526429c89db4c739e1e65942ca893)
Signed-off-by: Andres Smith <andressmithdev@pm.me>
* Fix faster-whisper backend and refactor transcription formatting to also work on CLI
Signed-off-by: Andres Smith <andressmithdev@pm.me>
(cherry picked from commit 69a93977d5e113eb7172bd85a0f918592d3d2168)
Signed-off-by: Andres Smith <andressmithdev@pm.me>
---------
Signed-off-by: Andres Smith <andressmithdev@pm.me>
Co-authored-by: nanoandrew4 <nanoandrew4@gmail.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat(tts): add support for streaming mode
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Send first audio, make sure it's 16
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(realtime): Add audio conversations
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore(realtime): Vendor the updated API and modify for server side
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(realtime): Update to the GA realtime API
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* chore: Document realtime API and add docs to AGENTS.md
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat: Filter reasoning from spoken output
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(realtime): Send delta and done events for tool calls and audio transcripts
Ensure that content is sent in both deltas and done events for function call arguments and audio transcripts. This fixes compatibility with clients that rely on delta events for parsing.
💘 Generated with Crush
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* fix(realtime): Improve tool call handling and error reporting
- Refactor Model interface to accept []types.ToolUnion and *types.ToolChoiceUnion
instead of JSON strings, eliminating unnecessary marshal/unmarshal cycles
- Fix Parameters field handling: support both map[string]any and JSON string formats
- Add PredictConfig() method to Model interface for accessing model configuration
- Add comprehensive debug logging for tool call parsing and function config
- Add missing return statement after prediction error (critical bug fix)
- Add warning logs for NoAction function argument parsing failures
- Improve error visibility throughout generateResponse function
💘 Generated with Crush
Assisted-by: Claude Sonnet 4.5 via Crush <crush@charm.land>
Signed-off-by: Richard Palethorpe <io@richiejp.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
exllama2 development has stalled and only old architectures are
supported. exllamav3 is still in development, meanwhile cleaning up
exllama2 from the gallery.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: allow to set forcing backends eviction while requests are in flight
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: try to make the request sit and retry if eviction couldn't be done
Otherwise calls that in order to pass would need to shutdown other
backends would just fail.
In this way instead we make the request sit and retry eviction until it
succeeds. The thresholds can be configured by the user.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* add tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* expose settings to CLI
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
