mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-12-31 02:19:08 -05:00
Code Issues Packages Projects Releases Wiki Activity
4,406 Commits 64 Branches 133 Tags
61ba98d43d39f4ad43c8f2a8570886c1f71c19e1
Commit Graph

4406 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
LocalAI [bot]
61ba98d43d chore: ⬆️ Update ggml-org/llama.cpp to e725a1a982ca870404a9c4935df52466327bbd02 (#5984) 
⬆️ 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>
 2025-08-06 21:17:20 +00:00
Ettore Di Giacinto
b9a25b16e6 feat: add reasoning effort and metadata to template (#5981) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-06 21:56:05 +02:00
Ettore Di Giacinto
6a8149e1fd fix: build kokoro-hipblas on self-hosted 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-06 15:50:54 +02:00
Ettore Di Giacinto
9c2840ac38 feat(kokoro): complete kokoro integration (#5978) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-06 15:23:29 +02:00
Ettore Di Giacinto
20a70e1244 feat(backends): add KittenTTS (#5977) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-06 12:38:45 +02:00
Ettore Di Giacinto
3295a298f4 feat(webui): allow to specify image size (#5976) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-06 12:38:02 +02:00
Ettore Di Giacinto
da6f37f000 Update qwen-image.yaml 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-08-06 10:40:46 +02:00
Ettore Di Giacinto
c092633cd7 feat(models): add support to qwen-image (#5975) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-06 10:36:53 +02:00
Ettore Di Giacinto
7e2a522229 Update harmony.yaml 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-08-05 23:58:48 +02:00
LocalAI [bot]
03e8592450 chore: ⬆️ Update ggml-org/llama.cpp to fd1234cb468935ea087d6929b2487926c3afff4b (#5972) 
⬆️ 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>
 2025-08-05 23:14:43 +02:00
Ettore Di Giacinto
f207bd1427 Update backend.yml 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-08-05 23:14:11 +02:00
Ettore Di Giacinto
a5c0fe31c3 chore(models): add gpt-oss-120b (#5974) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-05 23:13:24 +02:00
Ettore Di Giacinto
c68907ac65 chore(models): add gpt-oss-20b (#5973) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-05 23:08:34 +02:00
Ettore Di Giacinto
9087ddc4de chore(deps): bump torch and sentence-transformers (#5969) 
* chore(deps): bump torch and sentence-transformers

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

* chore(ci): add backend build tests

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

* chore: move jobs to self-hosted

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-05 19:45:20 +02:00
Ettore Di Giacinto
33bebd5114 chore(deps): bump torch and diffusers (#5970) 
* chore(ci): add backend build tests

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

* chore(deps): bump torch and diffusers

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

* chore(ci): run diffusers/hipblas on self-hosted

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

* chore(ci): do not publish darwin if building from PRs

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-05 14:47:01 +02:00
LocalAI [bot]
2913676157 chore: ⬆️ Update ggml-org/llama.cpp to 41613437ffee0dbccad684fc744788bc504ec213 (#5968) 
⬆️ 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>
 2025-08-04 23:16:30 +02:00
LocalAI [bot]
e83652489c docs: ⬆️ update docs version mudler/LocalAI (#5967) 
⬆️ 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>
 2025-08-04 21:00:23 +00:00
Richard Palethorpe
d6274eaf4a chore(build): Rename sycl to intel (#5964) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
v3.3.2 		2025-08-04 11:01:28 +02:00
LocalAI [bot]
4d90971424 chore: ⬆️ Update ggml-org/llama.cpp to d31192b4ee1441bbbecd3cbf9e02633368bdc4f5 (#5965) 
⬆️ 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>
 2025-08-03 21:03:20 +00:00
Ettore Di Giacinto
90f5639639 feat(backends): allow backends to not have a metadata file (#5963) 
In this case we generate one on the fly and we infer the metadata we
can.

Obviously this have the side effect of not being able to register
potential aliases.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-03 16:47:02 +02:00
Ettore Di Giacinto
a35a701052 feat(backends): install from local path (#5962) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-03 14:24:50 +02:00
Ettore Di Giacinto
3d8ec72dbf chore(stable-diffusion): bump, set GGML_MAX_NAME (#5961) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-08-03 10:47:02 +02:00
LocalAI [bot]
2a9d675d62 chore: ⬆️ Update ggml-org/llama.cpp to 5c0eb5ef544aeefd81c303e03208f768e158d93c (#5959) 
⬆️ 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>
 2025-08-02 23:35:24 +02:00
LocalAI [bot]
c782e8abf1 chore: ⬆️ Update ggml-org/whisper.cpp to 0becabc8d68d9ffa6ddfba5240e38cd7a2642046 (#5958) 
⬆️ 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>
 2025-08-02 21:04:13 +00:00
LocalAI [bot]
a1e1942d83 docs: ⬆️ update docs version mudler/LocalAI (#5956) 
⬆️ 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>
 2025-08-01 22:14:23 +02:00
Dedy F. Setyawan
787302b204 fix(docs): Improve responsiveness of tables (#5954) 
Signed-off-by: Dedy F. Setyawan <dedyfajars@gmail.com>
 2025-08-01 22:13:53 +02:00
LocalAI [bot]
0b085089b9 chore: ⬆️ Update ggml-org/llama.cpp to daf2dd788066b8b239cb7f68210e090c2124c199 (#5951) 
⬆️ 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>
v3.3.1 		2025-08-01 08:25:36 +02:00
LocalAI [bot]
624f3b1fc8 feat(swagger): update swagger (#5950) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-07-31 21:04:23 +00:00
Richard Palethorpe
c07bc55fee fix(intel): Set GPU vendor on Intel images and cleanup (#5945) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-07-31 19:44:46 +02:00
Ettore Di Giacinto
173e0774c0 chore(model gallery): add flux.1-krea-dev-ggml (#5949) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-31 18:32:06 +02:00
Ettore Di Giacinto
8ece26ab7c chore(model gallery): add flux.1-dev-ggml-abliterated-v2-q8_0 (#5948) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-31 17:23:48 +02:00
Ettore Di Giacinto
d704cc7970 chore(model gallery): add flux.1-dev-ggml-q8_0 (#5947) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-31 17:13:19 +02:00
Ettore Di Giacinto
ab17baaae1 chore(capability): improve messages (#5944) 
* chore(capability): improve messages

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

* chore: isolate to constants, do not detect from the first gpu

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-31 16:25:19 +02:00
Ettore Di Giacinto
ca358fcdca feat(stablediffusion-ggml): allow to load loras (#5943) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-31 16:25:05 +02:00
Ettore Di Giacinto
9aadfd485f chore: update swagger (#5946) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-31 16:22:27 +02:00
LocalAI [bot]
da3b0850de chore: ⬆️ Update ggml-org/whisper.cpp to f7502dca872866a310fe69d30b163fa87d256319 (#5941) 
⬆️ 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>
 2025-07-31 09:26:30 +02:00
LocalAI [bot]
8b1e8b4cda chore: ⬆️ Update ggml-org/llama.cpp to e9192bec564780bd4313ad6524d20a0ab92797db (#5940) 
⬆️ 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>
 2025-07-31 09:26:02 +02:00
Ettore Di Giacinto
3d22bfc27c feat(stablediffusion-ggml): add support to ref images (flux Kontext) (#5935) 
* feat(stablediffusion-ggml): add support to ref images

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

* Add it to the model gallery

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-30 22:42:34 +02:00
Ettore Di Giacinto
4438b4361e chore(model gallery): add qwen_qwen3-30b-a3b-thinking-2507 (#5939) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-30 21:18:56 +02:00
Ettore Di Giacinto
04bad9a2da chore(model gallery): add arcee-ai_afm-4.5b (#5938) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-30 15:37:07 +02:00
Ettore Di Giacinto
8235e53602 chore(model gallery): add qwen_qwen3-30b-a3b-instruct-2507 (#5936) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-30 15:29:34 +02:00
LocalAI [bot]
eb5c3670f1 chore: ⬆️ Update ggml-org/llama.cpp to aa79524c51fb014f8df17069d31d7c44b9ea6cb8 (#5934) 
⬆️ 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>
 2025-07-29 21:05:00 +00:00
LocalAI [bot]
89e61fca90 chore: ⬆️ Update ggml-org/whisper.cpp to d0a9d8c7f8f7b91c51d77bbaa394b915f79cde6b (#5932) 
⬆️ 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>
 2025-07-29 08:02:01 +02:00
LocalAI [bot]
9d6efe8842 chore: ⬆️ Update leejet/stable-diffusion.cpp to f6b9aa1a4373e322ff12c15b8a0749e6dd6f0253 (#5930) 
⬆️ Update leejet/stable-diffusion.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>
 2025-07-29 08:01:30 +02:00
LocalAI [bot]
60726d16f2 chore: ⬆️ Update ggml-org/llama.cpp to 8ad7b3e65b5834e5574c2f5640056c9047b5d93b (#5931) 
⬆️ 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>
 2025-07-29 08:01:03 +02:00
LocalAI [bot]
9d7ec09ec0 docs: ⬆️ update docs version mudler/LocalAI (#5929) 
⬆️ 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>
 2025-07-28 21:03:44 +00:00
Ettore Di Giacinto
36179ffbed fix(backend gallery): intel images for python-based backends, re-add exllama2 (#5928) 
chore(backend gallery): fix intel images for python-based backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
v3.3.0 		2025-07-28 15:15:19 +02:00
LocalAI [bot]
d25145e641 chore: ⬆️ Update ggml-org/llama.cpp to bf78f5439ee8e82e367674043303ebf8e92b4805 (#5927) 
⬆️ 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>
 2025-07-27 21:08:32 +00:00
Ettore Di Giacinto
949e5b9be8 feat(rfdetr): add object detection API (#5923) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-27 22:02:51 +02:00
Ettore Di Giacinto
73ecb7f90b chore: drop assistants endpoint (#5926) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-07-27 21:06:09 +02:00