mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-01-04 01:30:08 -06:00
Code Issues Packages Projects Releases Wiki Activity
4,551 Commits 67 Branches 133 Tags
ad99399c6ec2eea318121b4f5cfecb6b59ea4182
Commit Graph

580 Commits

Author SHA1 Message Date
Richard Palethorpe
e6ebfd3ba1 feat(whisper-cpp): Convert to Purego and add VAD (#6087) 
* fix(ci): Avoid matching wrong backend with the same prefix

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* chore(whisper): Use Purego and enable VAD

This replaces the Whisper CGO bindings with our own Purego based module
to make compilation easier.

In addition this allows VAD models to be loaded by Whisper. There is not
much benefit now except that the same backend can be used for VAD and
transcription. Depending on upstream we may also be able to use GPU for
VAD in the future, but presently it is disabled.

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-08-28 17:25:18 +02:00
Ettore Di Giacinto
ead00a28b9 Add 'optimum-quanto' to requirements 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-08-28 13:32:03 +02:00
Ettore Di Giacinto
9621edb4c5 feat(diffusers): add support for wan2.2 (#6153) 
* feat(diffusers): add support for wan2.2

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(ci): use ttl.sh for PRs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add ftfy deps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Revert "chore(ci): use ttl.sh for PRs"

This reverts commit c9fc3ecf28.

* Simplify

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: do not pin torch/torchvision on cuda12

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-28 10:26:42 +02:00
Ettore Di Giacinto
7ce92f0646 fix: select portable environment if detected (#6158) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-28 10:00:54 +02:00
LocalAI [bot]
6a4ab3c1e0 chore: ⬆️ Update ggml-org/llama.cpp to fbef0fad7a7c765939f6c9e322fa05cd52cf0c15 (#6155) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-27 21:09:34 +00:00
LocalAI [bot]
21faa4114b chore: ⬆️ Update ggml-org/llama.cpp to 8b696861364360770e9f61a3422d32941a477824 (#6151) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-26 22:07:38 +00:00
Ettore Di Giacinto
e35ad56602 chore(docs): add backends README 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-26 19:39:05 +02:00
Ettore Di Giacinto
3be8b2d8e1 chore(refactor): cli -> cmd, update docs (#6148) 
* chore(refactor): cli -> cmd

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update README

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-26 19:07:10 +02:00
Ettore Di Giacinto
3c3f477854 feat(mlx-audio): Add mlx-audio backend (#6138) 
* feat(mlx-audio): Add mlx-audio backend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* improve loading

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* CI tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: set C_INCLUDE_PATH to point to python install

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-26 15:27:06 +02:00
LocalAI [bot]
0fc88b3cdf chore: ⬆️ Update ggml-org/llama.cpp to c4e9239064a564de7b94ee2b401ae907235a8fca (#6139) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-26 12:18:58 +02:00
LocalAI [bot]
1a0d06f3db chore: ⬆️ Update ggml-org/llama.cpp to 043fb27d3808766d8ea8195bbd12359727264402 (#6137) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-25 08:57:09 +02:00
LocalAI [bot]
5e1a8b3621 chore: ⬆️ Update ggml-org/whisper.cpp to 7745fcf32846006128f16de429cfe1677c963b30 (#6136) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-24 21:12:13 +00:00
Ettore Di Giacinto
960e51e527 chore(diffusers): support both src and reference_images in diffusers (#6135) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-24 22:03:08 +02:00
Ettore Di Giacinto
195aa22e77 chore(docs): update list of supported backends (#6134) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-24 20:09:19 +02:00
Ettore Di Giacinto
ff5d2dc8be Revert "fix(rfdetr): use cpu torch for cpu builds" (#6131) 
Revert "fix(rfdetr): use cpu torch for cpu builds (#6129)"

This reverts commit fec8a36b36.
 2025-08-24 11:41:08 +02:00
Ettore Di Giacinto
fec8a36b36 fix(rfdetr): use cpu torch for cpu builds (#6129) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-24 10:17:25 +02:00
Ettore Di Giacinto
5d4f5d2355 feat(backends): add CPU variant for diffusers backend (#6128) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-24 10:17:10 +02:00
LocalAI [bot]
057248008f chore: ⬆️ Update ggml-org/llama.cpp to 710dfc465a68f7443b87d9f792cffba00ed739fe (#6126) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-24 08:41:39 +02:00
Ettore Di Giacinto
9f2c9cd691 feat(llama.cpp): Add gfx1201 support (#6125) 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-08-23 23:06:01 +02:00
Ettore Di Giacinto
6971f71a6c Add mlx-vlm (#6119) 
* Add mlx-vlm

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add to CI workflows

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add requirements-mps.txt

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-23 23:05:30 +02:00
Ettore Di Giacinto
1ba66d00f5 feat: bundle python inside backends (#6123) 
* feat(backends): bundle python

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test ci

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* vllm on self-hosted

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add clang

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Try to fix it for Mac

* Relocate links only when is portable

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Make sure to call macosPortableEnv

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Use self-hosted for vllm

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-23 22:36:39 +02:00
Ettore Di Giacinto
259383cf5e chore(deps): bump llama.cpp to '45363632cbd593537d541e81b600242e0b3d47fc' (#6122) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-23 08:39:10 +02:00
Ettore Di Giacinto
0fd395d6ec feat(diffusers): add MPS version (#6121) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-22 23:14:54 +02:00
Ettore Di Giacinto
1d830ce7dd feat(mlx): add mlx backend (#6049) 
* chore: allow to install with pip

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* WIP

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Make the backend to build and actually work

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* List models from system only

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add script to build darwin python backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Run protogen in libbackend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Detect if mps is available across python backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* CI: try to build backend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Debug CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Index mlx-vlm

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Remove mlx-vlm

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Drop CI test

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-22 08:42:29 +02:00
LocalAI [bot]
6dccfb09f8 chore: ⬆️ Update ggml-org/llama.cpp to cd36b5e5c7fed2a3ac671dd542d579ca40b48b54 (#6118) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-22 07:57:27 +02:00
LocalAI [bot]
e4d9cf8349 chore: ⬆️ Update ggml-org/llama.cpp to 7a6e91ad26160dd6dfb33d29ac441617422f28e7 (#6116) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-20 21:05:39 +00:00
Ettore Di Giacinto
8193d18c7c feat(img2img): Add support to Qwen Image Edit (#6113) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-20 10:18:55 +02:00
LocalAI [bot]
2e4dc6456f chore: ⬆️ Update ggml-org/llama.cpp to fb22dd07a639e81c7415e30b146f545f1a2f2caf (#6112) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-20 09:01:36 +02:00
Ettore Di Giacinto
060037bcd4 Revert "chore(deps): bump transformers from 4.48.3 to 4.55.2 in /backend/python/coqui" (#6105) 
Revert "chore(deps): bump transformers from 4.48.3 to 4.55.2 in /backend/pyth…"

This reverts commit 27ce570844.
 2025-08-19 15:00:33 +02:00
Ettore Di Giacinto
d9da4676b4 Revert "chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/coqui" (#6104) 
Revert "chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/pyt…"

This reverts commit 42c7859ab1.
 2025-08-19 15:00:11 +02:00
Ettore Di Giacinto
5ef4c2e471 feat(diffusers): add torchvision to support qwen-image-edit (#6103) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-19 12:05:48 +02:00
dependabot[bot]
27ce570844 chore(deps): bump transformers from 4.48.3 to 4.55.2 in /backend/python/coqui (#6096) 
chore(deps): bump transformers in /backend/python/coqui

Bumps [transformers](https://github.com/huggingface/transformers) from 4.48.3 to 4.55.2.
- [Release notes](https://github.com/huggingface/transformers/releases)
- [Commits](https://github.com/huggingface/transformers/compare/v4.48.3...v4.55.2)

---
updated-dependencies:
- dependency-name: transformers
  dependency-version: 4.55.2
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-08-19 09:44:01 +00:00
dependabot[bot]
42c7859ab1 chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/coqui (#6099) 
chore(deps): bump torch in /backend/python/coqui

Bumps [torch](https://github.com/pytorch/pytorch) from 2.3.1+cxx11.abi to 2.8.0.
- [Release notes](https://github.com/pytorch/pytorch/releases)
- [Changelog](https://github.com/pytorch/pytorch/blob/main/RELEASE.md)
- [Commits](https://github.com/pytorch/pytorch/commits/v2.8.0)

---
updated-dependencies:
- dependency-name: torch
  dependency-version: 2.8.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-08-19 08:42:52 +00:00
Ettore Di Giacinto
e7e83d0fa6 Revert "chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/coqui" (#6102) 
Revert "chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8…"

This reverts commit c6dc1d86f1.
 2025-08-19 09:29:56 +02:00
dependabot[bot]
c6dc1d86f1 chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/coqui (#6095) 
chore(deps): bump intel-extension-for-pytorch in /backend/python/coqui

Bumps intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu.

---
updated-dependencies:
- dependency-name: intel-extension-for-pytorch
  dependency-version: 2.8.10+xpu
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-08-19 07:09:47 +00:00
dependabot[bot]
6fd2e1964d chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/coqui (#6097) 
Bumps [grpcio](https://github.com/grpc/grpc) from 1.71.0 to 1.74.0.
- [Release notes](https://github.com/grpc/grpc/releases)
- [Changelog](https://github.com/grpc/grpc/blob/master/doc/grpc_release_schedule.md)
- [Commits](https://github.com/grpc/grpc/compare/v1.71.0...v1.74.0)

---
updated-dependencies:
- dependency-name: grpcio
  dependency-version: 1.74.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-08-19 08:11:58 +02:00
LocalAI [bot]
4b9afc418b chore: ⬆️ Update ggml-org/whisper.cpp to fc45bb86251f774ef817e89878bb4c2636c8a58f (#6089) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-19 08:10:25 +02:00
LocalAI [bot]
e44ff8514b chore: ⬆️ Update ggml-org/llama.cpp to 6d7f1117e3e3285d0c5c11b5ebb0439e27920082 (#6088) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-19 08:09:49 +02:00
dependabot[bot]
2b6be10b6b chore(deps): bump protobuf from 6.31.0 to 6.32.0 in /backend/python/transformers (#6100) 
chore(deps): bump protobuf in /backend/python/transformers

Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 6.31.0 to 6.32.0.
- [Release notes](https://github.com/protocolbuffers/protobuf/releases)
- [Changelog](https://github.com/protocolbuffers/protobuf/blob/main/protobuf_release.bzl)
- [Commits](https://github.com/protocolbuffers/protobuf/commits)

---
updated-dependencies:
- dependency-name: protobuf
  dependency-version: 6.32.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-08-19 05:09:17 +00:00
Richard Palethorpe
ebd1db2f09 chore(ci): Build modified backends on PR (#6086) 
* chore(stablediffusion-ggml): rm redundant comment

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* chore(ci): Build modified backends on PR

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-08-18 17:56:34 +02:00
LocalAI [bot]
7920d75805 chore: ⬆️ Update ggml-org/llama.cpp to 21c17b5befc5f6be5992bc87fc1ba99d388561df (#6084) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-18 08:26:58 +00:00
LocalAI [bot]
9eed5ef872 chore: ⬆️ Update ggml-org/llama.cpp to 1fe00296f587dfca0957e006d146f5875b61e43d (#6079) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-16 21:10:03 +00:00
Richard Palethorpe
784bd5db33 chore(build): Use Purego with stablediffusion backend (#6067) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-08-16 12:21:29 +02:00
LocalAI [bot]
243e86176e chore: ⬆️ Update ggml-org/llama.cpp to 5e6229a8409ac786e62cb133d09f1679a9aec13e (#6070) 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-16 08:38:57 +02:00
LocalAI [bot]
9486b88a25 chore: ⬆️ Update ggml-org/whisper.cpp to 040510a132f0a9b51d4692b57a6abfd8c9660696 (#6069) 
⬆️ Update ggml-org/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-08-16 08:30:54 +02:00
Ettore Di Giacinto
22067e3384 chore(rocm): bump rocm image, add gfx1200 support (#6065) 
Fixes: https://github.com/mudler/LocalAI/issues/6044

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-15 16:36:54 +02:00
Ettore Di Giacinto
4fbd639463 chore(ci): fixup builds for darwin and hipblas 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-15 15:58:02 +02:00
Ettore Di Giacinto
70f7d0c25f Revert "chore(build): Convert stablediffusion-ggml backend to Purego (#5989)" (#6064) 
This reverts commit 94cb20ae7f.
 2025-08-15 15:18:40 +02:00
Ettore Di Giacinto
576e821298 chore(deps): bump llama.cpp to 'df36bce667bf14f8e538645547754386f9516326 (#6062) 
chore(deps): bump llama.cpp to 'df36bce667bf14f8e538645547754386f9516326'

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-15 13:28:15 +02:00
Ettore Di Giacinto
8ab51509cc Update Makefile 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-08-15 08:33:25 +02:00