Winograd convolutions were always disabled giving error when inference device was CPU.
This commit implement logic to disable Winograd convolutions only if CPU or NPU are declared.
* feat(initializer): do not specify backends to autoload
We can simply try to autoload the backends extracted in the asset dir.
This will allow to build variants of the same backend (for e.g. with different instructions sets),
so to have a single binary for all the variants.
Signed-off-by: mudler <mudler@localai.io>
* refactor(prepare): refactor out llama.cpp prepare steps
Make it so are idempotent and that we can re-build
Signed-off-by: mudler <mudler@localai.io>
* [TEST] feat(build): build noavx version along
Signed-off-by: mudler <mudler@localai.io>
* build: make build parallel
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* build: do not override CMAKE_ARGS
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* build: add fallback variant
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(huggingface-langchain): fail if no token is set
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(huggingface-langchain): rename
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: do not autoload local-store
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: give priority between the listed backends
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: mudler <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
fix: more places where we are installing grpc that need a version specified
fix: attempt to fix metal tests
fix: metal/brew is forcing an update, they don't have 1.58 available anymore
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* start breaking up the giant channel refactor now that it's better understood - easier to merge bites
Signed-off-by: Dave Lee <dave@gray101.com>
* add concurrency and base64 back in, along with new base64 tests.
Signed-off-by: Dave Lee <dave@gray101.com>
* Automatic rename of whisper.go's Result to TranscriptResult
Signed-off-by: Dave Lee <dave@gray101.com>
* remove pkg/concurrency - significant changes coming in split 2
Signed-off-by: Dave Lee <dave@gray101.com>
* fix comments
Signed-off-by: Dave Lee <dave@gray101.com>
* add list_model service as another low-risk service to get it out of the way
Signed-off-by: Dave Lee <dave@gray101.com>
* split backend config loader into seperate file from the actual config struct. No changes yet, just reduce cognative load with smaller files of logical blocks
Signed-off-by: Dave Lee <dave@gray101.com>
* rename state.go ==> application.go
Signed-off-by: Dave Lee <dave@gray101.com>
* fix lost import?
Signed-off-by: Dave Lee <dave@gray101.com>
---------
Signed-off-by: Dave Lee <dave@gray101.com>
* Bump oneapi-basekit, optimum and openvino
* Changed PERFORMANCE HINT to CUMULATIVE_THROUGHPUT
Minor latency change for first token but about 10-15% speedup on token generation.
runCommand ==> ffmpegCommand. No functional changes, but makes it clear to the security scanner and future developers that this function cannot run arbitrary commands
Signed-off-by: Dave Lee <dave@gray101.com>
* fix regression #1971
fixes regression #1971 introduced by intel_extension_for_transformers==1.4
* UseTokenizerTemplate and StopPrompt
Implementation of use_tokenizer_template and stopwords options
* feat(parler-tts): Add new backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parler-tts): try downgrade protobuf
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(parler-tts): add parler conda env
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Revert "feat(parler-tts): try downgrade protobuf"
This reverts commit bd5941d5cfc00676b45a99f71debf3c34249cf3c.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* deps: add grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: try to gen proto with same environment
* workaround
* Revert "fix: try to gen proto with same environment"
This reverts commit 998c745e2f.
* Workaround fixup
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
* fix: initial work towards not committing generated files to the repository
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* feat: improve build docs
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: remove unused folder from .dockerignore and .gitignore
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: attempt to fix extra backend tests
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: attempt to fix other tests
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: more test fixes
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: fix apple tests
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: more extras tests fixes
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: add GOBIN to PATH in docker build
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: extra tests and Dockerfile corrections
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: remove build dependency checks
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: add golang protobuf compilers to tests-linux action
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: ensure protogen is run for extra backend installs
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: use newer protobuf
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: more missing protoc binaries
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: missing dependencies during docker build
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: don't install grpc compilers in the final stage if they aren't needed
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: python-grpc-tools in 22.04 repos is too old
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: add a couple of extra build dependencies to Makefile
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* fix: unbreak container rebuild functionality
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
---------
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
* Enhance autogptq backend to support VL models
* update dependencies for autogptq
* remove redundant auto-gptq dependency
* Convert base64 to image_url for Qwen-VL model
* implemented model inference for qwen-vl
* remove user prompt from generated answer
* fixed write image error
* fixed use_triton issue when loading Qwen-VL model
---------
Co-authored-by: Binghua Wu <bingwu@estee.com>
* Streaming working
* Small fix for regression on CUDA and XPU
* use pip version of optimum[openvino]
* Update backend/python/transformers/transformers_server.py
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* Token streaming support
fix optimum[openvino] package in install.sh
* Token Streaming support
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* fixes#1775 and #1774
Add BitsAndBytes Quantization and fixes embedding on CUDA devices
* Manage 4bit and 8 bit quantization
Manage different BitsAndBytes options with the quantization: parameter in yaml
* fix compilation errors on non CUDA environment
* OpenVINO draft
First draft of OpenVINO integration in transformer backend
* first working implementation
* Streaming working
* Small fix for regression on CUDA and XPU
* use pip version of optimum[openvino]
* Update backend/python/transformers/transformers_server.py
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* Enhance autogptq backend to support VL models
* update dependencies for autogptq
* remove redundant auto-gptq dependency
* Convert base64 to image_url for Qwen-VL model
* implemented model inference for qwen-vl
* remove user prompt from generated answer
* fixed write image error
---------
Co-authored-by: Binghua Wu <bingwu@estee.com>
* test with gguf instead of ggml. Updates testPrompt to match? Adds debugging line to Dockerfile that I've found helpful recently.
* fix testPrompt slightly
* Sad Experiment: Test GH runner without metal?
* break apart CGO_LDFLAGS
* switch runner
* upstream llama.cpp disables Metal on Github CI!
* missed a dir from clean-tests
* CGO_LDFLAGS
* tmate failure + NO_ACCELERATE
* whisper.cpp has a metal fix
* do the exact opposite of the name of this branch, but keep it around for unrelated fixes?
* add back newlines
* add tmate to linux for testing
* update fixtures
* timeout for tmate
* fix: clean up Makefile dependencies to allow for parallel builds
* refactor: remove old unused backend from Makefile
* fix: finish removing legacy backend, update piper
* fix: I broke llama... I fixed llama
* feat: give the tests and builds a few threads
* fix: ensure libraries are replaced before build, add dropreplace target
* Fix image build workflows
* feat(elevenlabs): map elevenlabs API support to TTS
This allows elevenlabs Clients to work automatically with LocalAI by
supporting the elevenlabs API.
The elevenlabs server endpoint is implemented such as it is wired to the
TTS endpoints.
Fixes: https://github.com/mudler/LocalAI/issues/1809
* feat(openai/tts): compat layer with openai tts
Fixes: #1276
* fix: adapt tts CLI
* fixes#1775 and #1774
Add BitsAndBytes Quantization and fixes embedding on CUDA devices
* Manage 4bit and 8 bit quantization
Manage different BitsAndBytes options with the quantization: parameter in yaml
* fix compilation errors on non CUDA environment
* feat(intel): add diffusers support
* try to consume upstream container image
* Debug
* Manually install deps
* Map transformers/hf cache dir to modelpath if not specified
* fix(compel): update initialization, pass by all gRPC options
* fix: add dependencies, implement transformers for xpu
* base it from the oneapi image
* Add pillow
* set threads if specified when launching the API
* Skip conda install if intel
* defaults to non-intel
* ci: add to pipelines
* prepare compel only if enabled
* Skip conda install if intel
* fix cleanup
* Disable compel by default
* Install torch 2.1.0 with Intel
* Skip conda on some setups
* Detect python
* Quiet output
* Do not override system python with conda
* Prefer python3
* Fixups
* exllama2: do not install without conda (overrides pytorch version)
* exllama/exllama2: do not install if not using cuda
* Add missing dataset dependency
* Small fixups, symlink to python, add requirements
* Add neural_speed to the deps
* correctly handle model offloading
* fix: device_map == xpu
* go back at calling python, fixed at dockerfile level
* Exllama2 restricted to only nvidia gpus
* Tokenizer to xpu
* fix: use vllm AsyncLLMEngine to bring true stream
Current vLLM implementation uses the LLMEngine, which was designed for offline batch inference, which results in the streaming mode outputing all blobs at once at the end of the inference.
This PR reworks the gRPC server to use asyncio and gRPC.aio, in combination with vLLM's AsyncLLMEngine to bring true stream mode.
This PR also passes more parameters to vLLM during inference (presence_penalty, frequency_penalty, stop, ignore_eos, seed, ...).
* Remove unused import
This PR specifically introduces a `core` folder and moves the following packages over, without any other changes:
- `api/backend`
- `api/config`
- `api/options`
- `api/schema`
Once this is merged and we confirm there's no regressions, I can migrate over the remaining changes piece by piece to split up application startup, backend services, http, and mqtt as was the goal of the earlier PRs!
