Commit Graph

4464 Commits

Author SHA1 Message Date
Ettore Di Giacinto
089efe05fd feat(backends): add system backend, refactor (#6059)
- Add a system backend path
- Refactor and consolidate system information in system state
- Use system state in all the components to figure out the system paths
  to used whenever needed
- Refactor BackendConfig -> ModelConfig. This was otherway misleading as
  now we do have a backend configuration which is not the model config.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-14 19:38:26 +02:00
Ettore Di Giacinto
253b7537dc fix(llama-cpp/darwin): make sure to bundle libutf8 libs (#6060)
fix(darwin): make sure to bundle libutf8_validity

Plus some refactoring, use makefile

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-14 17:56:35 +02:00
Ettore Di Giacinto
19c92c70c5 fix(backend-detection): default to CPU if there is less than 4GB of GPU available (#6057)
fix(gpu-detection): default to CPU if there is less than 4GB of GPU available

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-14 16:57:33 +02:00
Ettore Di Giacinto
b52bfaf1b3 fix: do not show invalid backends (#6058)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-14 13:01:56 +02:00
Ettore Di Giacinto
bf60ca5bf0 Update Makefile
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-08-14 11:53:43 +02:00
LocalAI [bot]
2b44467bd1 chore: ⬆️ Update ggml-org/llama.cpp to 29c8fbe4e05fd23c44950d0958299e25fbeabc5c (#6054)
⬆️ 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>
2025-08-14 09:19:15 +02:00
LocalAI [bot]
8c1f4a131e chore: ⬆️ Update ggml-org/whisper.cpp to 16c2924cb2c4b5c9f79220aa7708eb5b346b029b (#6055)
⬆️ 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>
2025-08-13 21:08:22 +00:00
Ettore Di Giacinto
10a3f0bd92 fix: chmod grpc processes only if needed (#6051)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-13 12:08:53 +02:00
LocalAI [bot]
72f4d541d0 chore: ⬆️ Update ggml-org/llama.cpp to f4586ee5986d6f965becb37876d6f3666478a961 (#6048)
⬆️ 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>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-08-13 08:33:48 +02:00
LocalAI [bot]
9f812fdb84 chore: ⬆️ Update ggml-org/whisper.cpp to 5527454cdb3e15d7e2b8a6e2afcb58cb61651fd2 (#6047)
⬆️ 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>
2025-08-12 21:12:07 +00:00
LocalAI [bot]
b70ee45fff docs: ⬆️ update docs version mudler/LocalAI (#6046)
⬆️ Update docs version mudler/LocalAI

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-08-12 22:05:50 +02:00
dependabot[bot]
9d9c853541 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/transformers (#6013)
chore(deps): bump grpcio in /backend/python/transformers

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>
2025-08-12 22:05:16 +02:00
Ettore Di Giacinto
18fcd8557c fix(llama.cpp): support gfx1200 (#6045)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-12 22:04:30 +02:00
dependabot[bot]
d8e27c38d7 chore(deps): bump oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu in /backend/python/common/template (#6016)
chore(deps): bump oneccl-bind-pt in /backend/python/common/template

Bumps oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu.

---
updated-dependencies:
- dependency-name: oneccl-bind-pt
  dependency-version: 2.8.0+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>
2025-08-12 18:57:20 +00:00
dependabot[bot]
3b0dc87932 chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/common/template (#6025)
chore(deps): bump torch in /backend/python/common/template

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>
2025-08-12 17:58:33 +00:00
dependabot[bot]
2374485222 chore(deps): bump actions/download-artifact from 4 to 5 (#6015)
Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 4 to 5.
- [Release notes](https://github.com/actions/download-artifact/releases)
- [Commits](https://github.com/actions/download-artifact/compare/v4...v5)

---
updated-dependencies:
- dependency-name: actions/download-artifact
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-08-12 18:54:57 +02:00
dependabot[bot]
0ca1765c17 chore(deps): bump actions/checkout from 4 to 5 (#6014)
Bumps [actions/checkout](https://github.com/actions/checkout) from 4 to 5.
- [Release notes](https://github.com/actions/checkout/releases)
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/checkout/compare/v4...v5)

---
updated-dependencies:
- dependency-name: actions/checkout
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-08-12 18:54:39 +02:00
dependabot[bot]
90b5ed9a1e chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/common/template (#6034)
chore(deps): bump intel-extension-for-pytorch

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>
2025-08-12 18:44:33 +02:00
dependabot[bot]
d438b769da chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/bark (#6043)
chore(deps): bump intel-extension-for-pytorch in /backend/python/bark

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>
2025-08-12 18:44:05 +02:00
dependabot[bot]
2e4bd1e33d chore(deps): bump oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu in /backend/python/rerankers (#6021)
chore(deps): bump oneccl-bind-pt in /backend/python/rerankers

Bumps oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu.

---
updated-dependencies:
- dependency-name: oneccl-bind-pt
  dependency-version: 2.8.0+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>
2025-08-12 16:04:54 +00:00
dependabot[bot]
ff73800970 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/exllama2 (#6019)
chore(deps): bump grpcio in /backend/python/exllama2

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>
2025-08-12 16:42:46 +02:00
Richard Palethorpe
94cb20ae7f chore(build): Convert stablediffusion-ggml backend to Purego (#5989)
* Try converting SD to purego

* chore(build): Use Purego with stablediffusion backend

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

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2025-08-12 16:42:15 +02:00
dependabot[bot]
47c20f9adb chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/rerankers (#6022)
chore(deps): bump grpcio in /backend/python/rerankers

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>
2025-08-12 15:24:48 +02:00
dependabot[bot]
a7fe153630 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/bark (#6033)
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>
2025-08-12 15:16:00 +02:00
dependabot[bot]
27519d2233 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/common/template (#6035)
chore(deps): bump grpcio in /backend/python/common/template

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>
2025-08-12 15:15:28 +02:00
dependabot[bot]
8cab0f880b chore(deps): bump sentence-transformers from 5.0.0 to 5.1.0 in /backend/python/transformers (#6028)
chore(deps): bump sentence-transformers in /backend/python/transformers

Bumps [sentence-transformers](https://github.com/UKPLab/sentence-transformers) from 5.0.0 to 5.1.0.
- [Release notes](https://github.com/UKPLab/sentence-transformers/releases)
- [Commits](https://github.com/UKPLab/sentence-transformers/compare/v5.0.0...v5.1.0)

---
updated-dependencies:
- dependency-name: sentence-transformers
  dependency-version: 5.1.0
  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>
2025-08-12 15:15:07 +02:00
dependabot[bot]
8c48b250c4 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/diffusers (#6037)
chore(deps): bump grpcio in /backend/python/diffusers

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>
2025-08-12 15:14:35 +02:00
dependabot[bot]
ba802c2ee4 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/vllm (#6036)
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>
2025-08-12 15:14:15 +02:00
Ettore Di Giacinto
429bb7a88c chore(model gallery): add baichuan-inc_baichuan-m2-32 (#6042)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-12 09:43:13 +02:00
LocalAI [bot]
b2e8b6d1aa chore: ⬆️ Update ggml-org/llama.cpp to be48528b068111304e4a0bb82c028558b5705f05 (#6012)
⬆️ 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>
v3.4.0
2025-08-11 21:06:10 +00:00
LocalAI [bot]
fba5b557a1 chore: ⬆️ Update ggml-org/whisper.cpp to b02242d0adb5c6c4896d59ac86d9ec9fe0d0fe33 (#6009)
⬆️ 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>
2025-08-11 12:54:41 +02:00
LocalAI [bot]
6db19c5cb9 chore: ⬆️ Update ggml-org/llama.cpp to 79c1160b073b8148a404f3dd2584be1606dccc66 (#6006)
⬆️ 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>
2025-08-11 12:54:21 +02:00
Ettore Di Giacinto
5428678209 chore(ci): more cleanup
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-11 10:10:38 +02:00
LocalAI [bot]
06129139eb chore(model-gallery): ⬆️ update checksum (#6010)
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2025-08-11 07:54:01 +02:00
Ettore Di Giacinto
05757e2738 feat(backends install): allow to specify name and alias during manual installation (#5971)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-10 10:05:53 +02:00
Ettore Di Giacinto
240b790f29 chore(model gallery): add impish_nemo_12b (#6007)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-10 10:05:20 +02:00
Ettore Di Giacinto
5f221f5946 fix(l4t-diffusers): add sentencepiece (#6005)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-09 09:08:35 +02:00
LocalAI [bot]
def7cdc0bf chore: ⬆️ Update ggml-org/llama.cpp to cd6983d56d2cce94ecb86bb114ae8379a609073c (#6003)
⬆️ 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>
2025-08-09 08:41:58 +02:00
Ettore Di Giacinto
ea9bf3dba2 Update backend.yml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-08-08 23:00:47 +02:00
Ettore Di Giacinto
b8eca530b6 feat(diffusers): add builds for nvidia-l4t (#6004)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 22:48:38 +02:00
Ettore Di Giacinto
47034ddacd chore(deps): bump edgevpn (#6001)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 16:23:18 +02:00
Ettore Di Giacinto
9a41331855 chore(model gallery): add outetts (#6000)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 12:55:58 +02:00
Ettore Di Giacinto
facc0181df chore(model gallery): add chatterbox (#5999)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 12:53:13 +02:00
Ettore Di Giacinto
4733adb983 chore: add Dia to the model gallery, fix backend (#5998)
* fix: correctly call OuteTTS and DiaTTS

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

* chore(model gallery): add dia

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 12:40:16 +02:00
Ettore Di Giacinto
326fda3223 chore(model gallery): add tarek07_nomad-llama-70b (#5997)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 12:06:20 +02:00
Ettore Di Giacinto
abf61e5b42 chore(model gallery): add openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix (#5996)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 11:14:46 +02:00
Ettore Di Giacinto
2ae45e7635 chore(model gallery): add huihui-ai_huihui-gpt-oss-20b-bf16-abliterated (#5995)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-08-08 11:01:52 +02:00
lnnt
7d41551e10 docs: update links in advanced-usage and models documentation (#5994)
* docs: update links in advanced-usage and models documentation

* docs: update links in advanced-usage and models documentation
2025-08-08 10:23:42 +02:00
LocalAI [bot]
6fbd720515 chore: ⬆️ Update ggml-org/whisper.cpp to 4245c77b654cd384ad9f53a4a302be716b3e5861 (#5993)
⬆️ 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>
2025-08-08 08:07:17 +02:00
LocalAI [bot]
4e40a8d1ed chore: ⬆️ Update ggml-org/llama.cpp to a0552c8beef74e843bb085c8ef0c63f9ed7a2b27 (#5992)
⬆️ 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>
2025-08-07 21:13:14 +00:00