mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-01-05 01:59:53 -06:00
Code Issues Packages Projects Releases Wiki Activity
3,776 Commits 68 Branches 133 Tags
ece239966f0a6029dfbf0eb75f55d3cda7380467
Commit Graph

3776 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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>
v2.27.0 		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
Ettore Di Giacinto
f926d2a72b chore(model gallery): thoughtless-fallen-abomination-70b-r1-v4.1-i1 (#5083) 2025-03-28 15:11:54 +01:00
Ettore Di Giacinto
ddeb9ed93e chore(model gallery): qwen2.5-14b-instruct-1m-unalign-i1 (#5082) 2025-03-28 15:08:33 +01:00
Ettore Di Giacinto
c7e99c7b59 chore(model gallery): gemma-3-starshine-12b-i1 (#5081) 2025-03-28 14:50:39 +01:00
Ettore Di Giacinto
6fabc92e56 chore(model gallery): add soob3123_amoral-gemma3-12b-v2 (#5080) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-28 14:45:02 +01:00
LocalAI [bot]
4645b3c919 chore: ⬆️ Update ggml-org/llama.cpp to 5dec47dcd411fdf815a3708fd6194e2b13d19006 (#5079) 
⬆️ 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>
 2025-03-27 23:32:33 +00:00
Dave
134fe2705c fix: ensure git-lfs is present (#5078) 
devcontainer clean builds had issue with git-lfs -- should this be installed for _all_ images for safety?

Signed-off-by: Dave Lee <dave@gray101.com>
 2025-03-27 22:23:28 +01:00
LocalAI [bot]
3cca32ba7e chore: ⬆️ Update ggml-org/llama.cpp to b3298fa47a2d56ae892127ea038942ab1cada190 (#5077) 
⬆️ 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>
 2025-03-27 10:47:07 +01:00
Ettore Di Giacinto
c069e61b26 chore(model gallery): add textsynth-8b-i1 (#5076) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-26 14:40:19 +01:00
Ettore Di Giacinto
7fa159e164 chore(model gallery): add blacksheep-24b-i1 (#5075) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-26 14:37:30 +01:00