mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-04-29 11:37:40 -04:00
Code Issues Packages Projects Releases Wiki Activity
6,092 Commits 95 Branches 143 Tags
8bb1e8f21fa1303fc87f01313bb70e14552f5c6a
Commit Graph

1340 Commits

Author SHA1 Message Date
LocalAI [bot]
047bc48fa9 chore(model gallery): 🤖 add 1 new models via gallery agent (#9464) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-04-21 11:07:07 +02:00
sec171
01bd8ae5d0 [gallery] Fix duplicate sha256 keys in Wan models (#9461) 
Fix duplicate sha256 keys in wan models gallery

The wan models previously defined the `sha256` key twice in their files lists,
which triggered strict mapping key checks in the YAML parser and resulted
in unmarshal errors that crashed the `/api/models` loading. This removes
the redundant trailing `sha256` keys from the Wan model definitions.

Assisted-by: Antigravity:Gemini-3.1-Pro-High [multi_replace_file_content, run_command]

Signed-off-by: Alex <codecrusher24@gmail.com>
 2026-04-21 11:06:36 +02:00
LocalAI [bot]
d9808769be chore(model-gallery): ⬆️ update checksum (#9451) 
⬆️ 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>
 2026-04-21 00:07:58 +02:00
Ettore Di Giacinto
8ab56e2ad3 feat(gallery): add wan i2v 720p (#9457) 
feat(gallery): add Wan 2.1 I2V 14B 720P + pin all wan ggufs by sha256

Adds a new entry for the native-720p image-to-video sibling of the
480p I2V model (wan-2.1-i2v-14b-480p-ggml). The 720p I2V model is
trained purely as image-to-video — no first-last-frame interpolation
path — so motion is freer than repurposing the FLF2V 720P variant as
an i2v. Shares the same VAE, umt5_xxl text encoder, and clip_vision_h
auxiliary files as the existing 480p I2V and 720p FLF2V entries, so
no new aux downloads are introduced.

Also pins the main diffusion gguf by sha256 for the new entry and for
the three existing wan entries that were previously missing a hash
(wan-2.1-t2v-1.3b-ggml, wan-2.1-i2v-14b-480p-ggml,
wan-2.1-flf2v-14b-720p-ggml). Hashes were fetched from HuggingFace's
x-linked-etag header per .agents/adding-gallery-models.md.

Assisted-by: Claude:claude-opus-4-7
 2026-04-20 23:34:11 +02:00
Ettore Di Giacinto
f683231811 feat(gallery): add Wan 2.1 FLF2V 14B 720P (#9440) 
First-last-frame-to-video variant of the 14B Wan family. Accepts a
start and end reference image and — unlike the pure i2v path — runs
both through clip_vision, so the final frame lands on the end image
both in pixel and semantic space. Right pick for seamless loops
(start_image == end_image) and narrative A→B cuts.

Shares the same VAE, umt5_xxl text encoder, and clip_vision_h as the
I2V 14B entry. Options block mirrors i2v's full-list-in-override
style so the template merge doesn't drop fields.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-20 10:34:36 +02:00
LocalAI [bot]
960757f0e8 chore(model gallery): 🤖 add 1 new models via gallery agent (#9436) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-04-20 08:48:47 +02:00
LocalAI [bot]
cb77a5a4b9 chore(model gallery): 🤖 add 1 new models via gallery agent (#9425) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-04-20 00:42:44 +02:00
Ettore Di Giacinto
9e44944cc1 fix(i2v): Add new options to the model configuration 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-04-20 00:27:05 +02:00
Ettore Di Giacinto
b27de08fff chore(gallery): fixup wan 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-19 21:31:22 +00:00
Ettore Di Giacinto
054c4b4b45 feat(stable-diffusion.ggml): add support for video generation (#9420) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-19 09:26:33 +02:00
LocalAI [bot]
844b0b760b chore(model gallery): 🤖 add 1 new models via gallery agent (#9400) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-04-17 17:56:41 +02:00
LocalAI [bot]
55c05211d3 chore(model gallery): 🤖 add 1 new models via gallery agent (#9399) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-04-17 16:10:02 +02:00
LocalAI [bot]
ec5935421c chore(model-gallery): ⬆️ update checksum (#9384) 
⬆️ 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>
 2026-04-16 22:41:52 +02:00
Matt Van Horn
c4f309388e fix(gallery): correct gemma-4 model URIs returning 404 (#9379) 
The gemma-4-26b-a4b-it, gemma-4-e2b-it, and gemma-4-e4b-it gallery
entries pointed at files that do not exist on HuggingFace, so LocalAI
fails with 404 when users try to install them.

Two issues per entry:
- mmproj filename uses the 'f16' quantization suffix, but ggml-org
  publishes the mmproj projectors as 'bf16'.
- The e2b and e4b URIs hardcode lowercase 'e2b'/'e4b' in the filename
  component. HuggingFace file paths are case-sensitive and the real
  files use uppercase 'E2B'/'E4B'.

Updated filename, uri, sha256, and the top-level 'mmproj' and
'parameters.model' references so every entry points at a real file
and the declared hashes match the content.

Verified each URI resolves (HTTP 302) and each sha256 matches the
'x-linked-etag' header returned by HuggingFace.

Signed-off-by: Matt Van Horn <mvanhorn@gmail.com>
 2026-04-16 08:51:20 +02:00
LocalAI [bot]
08445b1b89 chore(model-gallery): ⬆️ update checksum (#9369) 
⬆️ 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>
 2026-04-16 01:12:01 +02:00
LocalAI [bot]
8487058673 chore(model-gallery): ⬆️ update checksum (#9358) 
⬆️ 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>
 2026-04-15 01:25:59 +02:00
Ettore Di Giacinto
b361d2ddd6 chore(gallery): add new llama.cpp supported models (qwen-asr, ocr) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-14 10:04:50 +00:00
LocalAI [bot]
c6d5dc3374 chore(model-gallery): ⬆️ update checksum (#9346) 
⬆️ 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>
 2026-04-13 23:00:13 +02:00
Ettore Di Giacinto
be1b8d56c9 fix(gallery): override parameters for flux kontext 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-04-13 22:29:17 +02:00
Ettore Di Giacinto
7a0e6ae6d2 feat(qwen3tts.cpp): add new backend (#9316) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-11 23:14:26 +02:00
LocalAI [bot]
7edd3ea96f chore(model-gallery): ⬆️ update checksum (#9321) 
⬆️ 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>
 2026-04-11 22:53:48 +02:00
thelittlefireman
7c1865b307 Fix load of z-image-turbo (#9264) 
* Fix load of z-image and improve speed

Signed-off-by: thelittlefireman <5165783+thelittlefireman@users.noreply.github.com>

* Remove diffusion_flash_attn from z-image-ggml.yaml

Removed 'diffusion_flash_attn' parameter from configuration.

Signed-off-by: thelittlefireman <5165783+thelittlefireman@users.noreply.github.com>

---------

Signed-off-by: thelittlefireman <5165783+thelittlefireman@users.noreply.github.com>
 2026-04-11 08:42:13 +02:00
Ettore Di Giacinto
706cf5d43c feat(sam.cpp): add sam.cpp detection backend (#9288) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-09 21:49:11 +02:00
Ettore Di Giacinto
b64347b6aa chore: add gemma4 to the gallery 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-08 23:44:16 +00:00
Ettore Di Giacinto
285f7d4340 chore: add embeddingemma 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-08 17:40:55 +00:00
Richard Palethorpe
ea6e850809 feat: Add Kokoros backend (#9212) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-04-08 19:23:16 +02:00
ER-EPR
39c954764c Update index.yaml and add Qwen3.5 model files (#9237) 
* Update index.yaml

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

* Add mmproj files for Qwen3.5 models

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

* Update file paths for Qwen models in index.yaml

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

* Update index.yaml

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

* Refactor Qwen3-Reranker-0.6B entry in index.yaml

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

* Update qwen3.yaml configuration parameters

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

---------

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>
 2026-04-05 09:21:21 +02:00
Ettore Di Giacinto
9b7d5513fc chore(gallery): add mmproj file for gemma4 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-04-05 02:02:52 +02:00
LocalAI [bot]
d990f2790c chore(model-gallery): ⬆️ update checksum (#9233) 
⬆️ 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>
 2026-04-04 23:02:41 +02:00
LocalAI [bot]
e4ee74354f chore(model gallery): 🤖 add 1 new models via gallery agent (#9210) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-04-03 16:23:17 +02:00
LocalAI [bot]
e9f10f2f50 chore(model gallery): 🤖 add 1 new models via gallery agent (#9202) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-04-02 21:22:19 +02:00
ER-EPR
afe79568d6 fix: huggingface repo change the file name so Update index.yaml is needed (#9163) 
* Update index.yaml

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

* Add mmproj files for Qwen3.5 models

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

* Update file paths for Qwen models in index.yaml

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>

---------

Signed-off-by: ER-EPR <38782737+ER-EPR@users.noreply.github.com>
 2026-03-30 00:48:17 +02:00
Richard Palethorpe
87b3e10024 fix(flux.2-klein-9b): Use Qwen3-8b to avoid GGML assertion failure on tensor mismatch (#8995) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2026-03-13 21:39:31 +01:00
Ettore Di Giacinto
ec91c477dc Remove model descriptions from index.yaml 
Removed description fields from multiple model entries in index.yaml.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-03-12 21:43:21 +01:00
LocalAI [bot]
3b9abffdc8 chore(model-gallery): ⬆️ update checksum (#8985) 
⬆️ 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>
 2026-03-12 21:34:27 +01:00
Ettore Di Giacinto
a738f8b0e4 feat(backends): add ace-step.cpp (#8965) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-03-12 18:56:26 +01:00
Ettore Di Giacinto
8f3efaed15 Update model entry in index.yaml 
Removed description and license fields from model entry.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-03-12 18:51:29 +01:00
LocalAI [bot]
c4cccb728e chore(model gallery): 🤖 add 1 new models via gallery agent (#8980) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-03-12 18:51:00 +01:00
Ettore Di Giacinto
b209947e81 Remove Qwen3.5-35B model and update model path 
Removed deprecated Qwen3.5-35B-A3B model configuration and updated model path for Qwen3.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-03-12 18:19:55 +01:00
Ettore Di Giacinto
7dc691c171 feat: add fish-speech backend (#8962) 
* feat: add fish-speech backend

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

* drop portaudio

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-03-12 07:48:23 +01:00
Ettore Di Giacinto
17f36e73b5 Remove model name entries from index.yaml 
Removed 'name' entries for various models in the index file.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-03-12 01:13:58 +01:00
Ettore Di Giacinto
031909d85a Clean up gallery index by removing obsolete models 
Removed multiple models and their associated metadata from the gallery index.

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2026-03-12 00:55:19 +01:00
LocalAI [bot]
79f90de935 chore(model-gallery): ⬆️ update checksum (#8945) 
⬆️ 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>
 2026-03-10 21:43:52 +01:00
LocalAI [bot]
bda826d005 chore(model gallery): 🤖 add 1 new models via gallery agent (#8939) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-03-10 18:09:11 +01:00
Ettore Di Giacinto
05a3d00924 chore(size): display size of HF models and allow to specify it from the gallery (#8907) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2026-03-09 17:38:14 +01:00
LocalAI [bot]
734b6d391f chore(model gallery): 🤖 add 1 new models via gallery agent (#8904) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-03-09 17:01:56 +01:00
LocalAI [bot]
66a7bd38d2 chore(model gallery): 🤖 add 1 new models via gallery agent (#8902) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-03-09 15:59:33 +01:00
LocalAI [bot]
564d7f49dd chore(model gallery): 🤖 add 1 new models via gallery agent (#8901) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-03-09 15:27:48 +01:00
LocalAI [bot]
06125c338a feat: update descriptions for first 9 models in gallery/index.yaml (#8831) 
feat: update descriptions for first 9 models in gallery/index.yaml from HuggingFace model cards

- Updated qwen3.5-27b-claude-4.6-opus-reasoning-distilled-i1 with reasoning capabilities
- Updated qwen3.5-4b-claude-4.6-opus-reasoning-distilled with reasoning capabilities
- Updated q3.5-bluestar-27b with fine-tuned variant description
- Updated qwen3.5-9b with multimodal capabilities
- Updated qwen3.5-397b-a17b with large-scale model description
- Updated qwen3.5-27b with performance-efficiency balance
- Updated qwen3.5-122b-a10b with MoE architecture description
- Updated qwen3.5-35b-a3b with MoE architecture description
- Updated qwen3-next-80b-a3b-thinking with next-gen model description

Descriptions sourced from HuggingFace model API metadata.

Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
 2026-03-07 12:34:29 +01:00
LocalAI [bot]
73158600c8 chore(model gallery): 🤖 add 1 new models via gallery agent (#8830) 
chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2026-03-07 09:17:30 +01:00