dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21
3785 commits 62 branches 113 tags 38 MiB
Commit graph

3785 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ettore Di Giacinto
b4df1c9cf3
fix(gemma): improve prompt for tool calls (#5142) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-08 10:12:42 +02:00
Ettore Di Giacinto
4fbd6609f2
chore(model gallery): add meta-llama_llama-4-scout-17b-16e-instruct (#5141) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-08 10:12:28 +02:00
Ettore Di Giacinto
7387932f89
chore(model gallery): add mensa-beta-14b-instruct-i1 (#5140) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-08 10:01:24 +02:00
Ettore Di Giacinto
59c37e67b2
chore(model gallery): add eurydice-24b-v2-i1 (#5139) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-08 09:56:29 +02:00
Ettore Di Giacinto
c09d227647
chore(model gallery): add watt-ai_watt-tool-70b (#5138) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-08 09:42:49 +02:00
Ettore Di Giacinto
547d322b28
chore(model gallery): add arliai_qwq-32b-arliai-rpr-v (#5137) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-08 09:40:26 +02:00
dependabot[bot]
a6f0bb410f
chore(deps): bump securego/gosec from 2.22.0 to 2.22.3 (#5134) 
Bumps [securego/gosec](https://github.com/securego/gosec) from 2.22.0 to 2.22.3.
- [Release notes](https://github.com/securego/gosec/releases)
- [Changelog](https://github.com/securego/gosec/blob/master/.goreleaser.yml)
- [Commits](https://github.com/securego/gosec/compare/v2.22.0...v2.22.3)

---
updated-dependencies:
- dependency-name: securego/gosec
  dependency-version: 2.22.3
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-04-07 21:09:45 +00:00
Ettore Di Giacinto
710f624ecd
fix(webui): improve model display, do not block view (#5133) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-07 18:03:25 +02:00
LocalAI [bot]
5018452be7
chore: ⬆️ Update ggml-org/llama.cpp to 916c83bfe7f8b08ada609c3b8e583cf5301e594b (#5130) 
⬆️ 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>
 2025-04-06 21:51:51 +00:00
Ettore Di Giacinto
ece239966f
chore: ⬆️ Update ggml-org/llama.cpp to 6bf28f0111ff9f21b3c1b1eace20c590281e7ba6 (#5127) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-06 14:01:51 +02:00
Ettore Di Giacinto
3b8bc7e64c
chore(model gallery): add open-thoughts_openthinker2-7b (#5129) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-06 10:53:22 +02:00
Ettore Di Giacinto
fc73b2b430
chore(model gallery): add open-thoughts_openthinker2-32b (#5128) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-06 10:48:21 +02:00
Ettore Di Giacinto
901dba6063
chore(model gallery): add gemma-3-27b-it-qat (#5124) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-05 08:46:49 +02:00
LocalAI [bot]
b88a7a4550
chore: ⬆️ Update ggml-org/llama.cpp to 3e1d29348b5d77269f6931500dd1c1a729d429c8 (#5123) 
⬆️ 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>
 2025-04-04 21:49:53 +00:00
Ettore Di Giacinto
106e40845f
chore(model gallery): add katanemo_arch-function-chat-3b (#5122) 2025-04-04 10:45:44 +02:00
Ettore Di Giacinto
0064bec8f5
chore(model gallery): add katanemo_arch-function-chat-1.5b (#5121) 2025-04-04 10:31:44 +02:00
Ettore Di Giacinto
9e6dbb0b5a
chore(model gallery): add katanemo_arch-function-chat-7b (#5120) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-04 10:29:47 +02:00
Ettore Di Giacinto
d26e61388b
chore(model gallery): add tesslate_synthia-s1-27b (#5119) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-04 10:27:52 +02:00
Ettore Di Giacinto
31a7084c75
chore(model gallery): add gemma-3-4b-it-qat (#5118) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-04 10:23:56 +02:00
Ettore Di Giacinto
128612a6fc
chore(model gallery): add gemma-3-12b-it-qat (#5117) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-04 10:21:45 +02:00
LocalAI [bot]
6af3f46bc3
chore: ⬆️ Update ggml-org/llama.cpp to c262beddf29f3f3be5bbbf167b56029a19876956 (#5116) 
⬆️ 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>
 2025-04-03 22:59:49 +00:00
Richard Palethorpe
d2cf8ef070
fix(sycl): kernel not found error by forcing -fsycl (#5115) 
* chore(sycl): Update oneapi to 2025:1

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

* fix(sycl): Pass -fsycl flag as workaround

-fsycl should be set by llama.cpp's cmake file, but something goes wrong
and it doesn't appear to get added

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

* fix(build): Speed up llama build by using all CPUs

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

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-04-03 16:22:59 +02:00
Ettore Di Giacinto
259ad3cfe6
chore(model gallery): add all-hands_openhands-lm-1.5b-v0.1 (#5114) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-03 10:25:46 +02:00
Ettore Di Giacinto
18b320d577
chore(deps): bump llama.cpp to 'f01bd02376f919b05ee635f438311be8dfc91d7c (#5110) 
chore(deps): bump llama.cpp to 'f01bd02376f919b05ee635f438311be8dfc91d7c'

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-03 10:23:14 +02:00
Ettore Di Giacinto
89e151f035
chore(model gallery): add all-hands_openhands-lm-7b-v0.1 (#5113) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-03 10:20:20 +02:00
Ettore Di Giacinto
22060f6410
chore(model gallery): add burtenshaw_gemmacoder3-12b (#5112) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-03 10:17:57 +02:00
Ettore Di Giacinto
7ee3288460
chore(model gallery): add all-hands_openhands-lm-32b-v0.1 (#5111) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-03 10:15:57 +02:00
LocalAI [bot]
cbbc954a8c
chore: ⬆️ Update ggml-org/llama.cpp to f423981ac806bf031d83784bcb47d2721bc70f97 (#5108) 
⬆️ 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>
 2025-04-02 09:22:53 +02:00
Ettore Di Giacinto
2c425e9c69
feat(loader): enhance single active backend by treating as singleton (#5107) 
feat(loader): enhance single active backend by treating at singleton

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-01 20:58:11 +02:00
LocalAI [bot]
c59975ab05
chore: ⬆️ Update ggml-org/llama.cpp to c80a7759dab10657b9b6c3e87eef988a133b9b6a (#5105) 
⬆️ 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>
 2025-04-01 00:01:34 +02:00
Ettore Di Giacinto
05f7004487
fix: race during stop of active backends (#5106) 
* chore: drop double call to stop all backends, refactors

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

* fix: do lock when cycling to models to delete

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-01 00:01:10 +02:00
Ettore Di Giacinto
2f9203cd2a
chore: drop remoteLibraryURL from kong vars (#5103) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-31 22:48:17 +02:00
LocalAI [bot]
f09b33f2ef
docs: ⬆️ update docs version mudler/LocalAI (#5104) 
⬆️ 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>
 2025-03-31 22:48:03 +02:00
Ettore Di Giacinto
65470b0ab1 Update README 2025-03-31 21:51:09 +02:00
Ettore Di Giacinto
9a23fe662b
Update README.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-03-31 19:35:34 +02:00
LocalAI [bot]
6d7ac09e96
chore: ⬆️ Update ggml-org/llama.cpp to 4663bd353c61c1136cd8a97b9908755e4ab30cec (#5100) 
⬆️ 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>
 2025-03-30 21:59:30 +00:00
Ettore Di Giacinto
c2a39e3639
fix(llama.cpp): properly handle sigterm (#5099) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-30 18:08:29 +02:00
Ettore Di Giacinto
ae625a4d00
chore(model gallery): add hammer2.0-7b (#5098) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-30 09:50:21 +02:00
Ettore Di Giacinto
7f3a029596
chore(model gallery): add forgotten-abomination-70b-v5.0 (#5097) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-30 09:48:24 +02:00
Ettore Di Giacinto
b34cf00819
chore(model gallery): add galactic-qwen-14b-exp1 (#5096) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-30 09:46:51 +02:00
LocalAI [bot]
d4a10b4300
chore: ⬆️ Update ggml-org/llama.cpp to 0bb2919335d00ff0bc79d5015da95c422de51f03 (#5095) 
⬆️ 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>
 2025-03-29 21:40:45 +00:00
Ettore Di Giacinto
9c74d74f7b
feat(gguf): guess default context size from file (#5089) 
feat(gguf): guess default config file from files

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-29 14:42:14 +01:00
Ettore Di Giacinto
679ee7bea4
chore(model gallery): add chaoticneutrals_very_berry_qwen2_7b (#5093) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-29 12:34:49 +01:00
Ettore Di Giacinto
77d7dc62c4
chore(model gallery): add tesslate_tessa-t1-3b (#5092) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-29 12:15:28 +01:00
Ettore Di Giacinto
699519d1fe
chore(model gallery): add tesslate_tessa-t1-7b (#5091) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-29 12:12:01 +01:00
Ettore Di Giacinto
8faf39d34e
chore(model gallery): add tesslate_tessa-t1-14b (#5090) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-29 11:58:39 +01:00
Ettore Di Giacinto
5d261a6fcd
chore(model gallery): add tesslate_tessa-t1-32b (#5088) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-29 11:53:47 +01:00
Ettore Di Giacinto
22d5727089
chore(model gallery): add tarek07_legion-v2.1-llama-70b (#5087) 2025-03-29 11:27:06 +01:00
LocalAI [bot]
c965197d6f
chore: ⬆️ Update ggml-org/llama.cpp to b4ae50810e4304d052e630784c14bde7e79e4132 (#5085) 
⬆️ 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>
 2025-03-28 21:37:18 +00:00
Ettore Di Giacinto
994a6c4939
chore(model gallery): fallen-safeword-70b-r1-v4.1 (#5084) 2025-03-28 15:20:38 +01:00