mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-01-03 11:59:25 -05:00
Code Issues Packages Projects Releases Wiki Activity
4,199 Commits 67 Branches 133 Tags
v3.1.0
Commit Graph

4199 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
LocalAI [bot]
6a650e68cb chore: ⬆️ Update ggml-org/whisper.cpp to 32cf4e2aba799aff069011f37ca025401433cf9f (#5733) 
⬆️ 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>
v3.1.0 		2025-06-26 22:09:26 +02:00
LocalAI [bot]
5e1373877a chore: ⬆️ Update ggml-org/llama.cpp to 8846aace4934ad29651ea61b8c7e3f6b0556e3d2 (#5734) 
⬆️ 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>
 2025-06-26 22:09:03 +02:00
Ettore Di Giacinto
b5b0ab26e7 fix(ci): remove non-existant input from build matrix 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-26 21:42:27 +02:00
Ettore Di Giacinto
9725bb4bbd chore(model gallery): add gemma-3n-e4b-it (#5731) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-26 19:36:50 +02:00
Ettore Di Giacinto
33b4275bbc chore(model gallery): add gemma-3n-e2b-it (#5730) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-26 19:35:49 +02:00
Ettore Di Giacinto
6644af10c6 feat: ⚠️ reduce images size and stop bundling sources (#5721) 
feat: reduce images size and stop bundling sources

Do not copy sources anymore, and reduce packages of the base images by
not using builder images.

If needed to rebuild, just build the container image from scratch by
following the docs. We will slowly try to migrate all backends to the
gallery to keep the core small.

This PR is a breaking change, it also sets the base folders to /models
and /backends instead of /build/models and /build/backends.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-26 18:41:38 +02:00
Ettore Di Giacinto
7c4a2e9b85 chore(ci): ⚠️ fix latest tag by using docker meta action (#5722) 
chore(ci): fix latest tag by using docker meta action

Also uniform tagging names

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-26 18:40:25 +02:00
Ettore Di Giacinto
bcccee3909 fix(backends gallery): delete dangling dirs if installation failed (#5729) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-26 17:38:03 +02:00
Ettore Di Giacinto
c6f50ddd0c Revert "chore: ⬆️ Update leejet/stable-diffusion.cpp to 10c6501bd05a697e014f1bee3a84e5664290c489" (#5727) 
Revert "chore: ⬆️ Update leejet/stable-diffusion.cpp to `10c6501bd05a…"

This reverts commit 30600dd5cb.
 2025-06-26 13:25:25 +02:00
LocalAI [bot]
6613373b1b chore: ⬆️ Update ggml-org/whisper.cpp to 4daf7050ca2bf17f5166f45ac6da651c4e33f293 (#5725) 
⬆️ 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>
 2025-06-26 13:00:20 +02:00
LocalAI [bot]
1659b3f795 chore: ⬆️ Update ggml-org/llama.cpp to 2bf9d539dd158345e3a3b096e16474af535265b4 (#5724) 
⬆️ 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>
 2025-06-26 12:59:57 +02:00
LocalAI [bot]
30600dd5cb chore: ⬆️ Update leejet/stable-diffusion.cpp to 10c6501bd05a697e014f1bee3a84e5664290c489 (#4925) 
⬆️ 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>
 2025-06-25 22:45:15 +00:00
Ettore Di Giacinto
179fcf5541 chore(model gallery): add menlo_jan-nano-128k (#5723) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-25 12:14:11 +02:00
LocalAI [bot]
9cb75086bb chore: ⬆️ Update ggml-org/whisper.cpp to 0083335ba0e9d6becbe0958903b0a27fc2ebaeed (#5718) 
⬆️ 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>
 2025-06-25 09:47:33 +02:00
LocalAI [bot]
594bb462ab chore: ⬆️ Update ggml-org/llama.cpp to 73e53dc834c0a2336cd104473af6897197b96277 (#5719) 
⬆️ 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>
 2025-06-24 22:47:48 +00:00
Ettore Di Giacinto
aa730a7b96 chore(model gallery): add delta-vector_austral-24b-winton (#5717) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-24 18:37:28 +02:00
Ettore Di Giacinto
0a454c527a chore(model gallery): add astrosage-70b (#5716) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-24 18:34:37 +02:00
Ettore Di Giacinto
cf86bcb984 chore(model gallery): add skywork_skywork-swe-32b (#5715) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-24 18:29:36 +02:00
Ettore Di Giacinto
a6d9988e84 feat(backend gallery): add meta packages (#5696) 
* feat(backend gallery): add meta packages

So we can have meta packages such as "vllm" that automatically installs
the corresponding package depending on the GPU that is being currently
detected in the system.

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

* feat: use a metadata file

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-24 17:08:27 +02:00
Ettore Di Giacinto
f3a114342e chore(model gallery): add mistralai_mistral-small-3.2-24b-instruct-2506 (#5714) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-24 13:59:14 +02:00
LocalAI [bot]
0d275ccc03 chore: ⬆️ Update ggml-org/llama.cpp to ce82bd0117bd3598300b3a089d13d401b90279c7 (#5712) 
⬆️ 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>
 2025-06-24 08:37:32 +02:00
LocalAI [bot]
58dba3f01c chore: ⬆️ Update ggml-org/whisper.cpp to a422176937c5bb20eb58d969995765f90d3c1a9b (#5713) 
⬆️ 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>
 2025-06-23 22:45:31 +00:00
kilavvy
b68d6e8088 Docs: Fix typos (#5709) 
* Update GPU-acceleration.md

Signed-off-by: kilavvy <140459108+kilavvy@users.noreply.github.com>

* Update image-generation.md

Signed-off-by: kilavvy <140459108+kilavvy@users.noreply.github.com>

---------

Signed-off-by: kilavvy <140459108+kilavvy@users.noreply.github.com>
 2025-06-23 18:15:06 +02:00
LocalAI [bot]
2352cec7e6 chore: ⬆️ Update ggml-org/llama.cpp to 238005c2dc67426cf678baa2d54c881701693288 (#5710) 
⬆️ 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>
 2025-06-22 22:43:41 +00:00
Ettore Di Giacinto
de72ae79b5 chore(model gallery): add ds-r1-qwen3-8b-arliai-rpr-v4-small-iq-imatrix (#5708) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-22 09:05:55 +02:00
Ettore Di Giacinto
884c07d5f9 chore(model gallery): add allura-org_q3-8b-kintsugi (#5707) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-22 09:04:49 +02:00
Ettore Di Giacinto
cca7cbef1e chore(model gallery): add qwen3-the-xiaolong-omega-directive-22b-uncensored-abliterated-i1 (#5706) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-22 09:01:08 +02:00
Ettore Di Giacinto
32cd0d03d4 chore(model gallery): add menlo_jan-nano (#5705) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-22 08:57:33 +02:00
Ettore Di Giacinto
ee4d9e83d0 Update stalebot.yml 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-22 08:51:13 +02:00
LocalAI [bot]
5547e08a30 chore: ⬆️ Update ggml-org/llama.cpp to aa0ef5c578eef4c2adc7be1282f21bab5f3e8d26 (#5703) 
⬆️ 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>
 2025-06-21 23:54:53 +02:00
LocalAI [bot]
ca7385c303 chore: ⬆️ Update ggml-org/whisper.cpp to e6c10cf3d5d60dc647eb6cd5e73d3c347149f746 (#5702) 
⬆️ 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>
 2025-06-21 23:54:28 +02:00
Ettore Di Giacinto
28759e79d3 chore(model gallery): add qwen3-the-josiefied-omega-directive-22b-uncensored-abliterated-i1 (#5704) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-21 23:54:05 +02:00
Ettore Di Giacinto
40249b6b84 Update stalebot.yml 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-21 22:38:23 +02:00
Ettore Di Giacinto
e09e47bada chore(ci): add stale bot (#5700) 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-21 20:12:08 +02:00
Ettore Di Giacinto
3796558aeb Update quickstart.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-21 20:11:57 +02:00
LocalAI [bot]
cca4f010f8 chore: ⬆️ Update ggml-org/llama.cpp to 06cbedfca1587473df9b537f1dd4d6bfa2e3de13 (#5697) 
⬆️ 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>
 2025-06-20 22:44:39 +00:00
Ettore Di Giacinto
be3ff482d0 chore(ci): try to optimize disk space when tagging latest (#5695) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-20 15:54:14 +02:00
LocalAI [bot]
af255cd0be chore: ⬆️ Update ggml-org/llama.cpp to 8f71d0f3e86ccbba059350058af8758cafed73e6 (#5692) 
⬆️ 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>
 2025-06-20 15:53:55 +02:00
LocalAI [bot]
8000228d1b chore: ⬆️ Update ggml-org/whisper.cpp to 3e65f518ddf840b13b74794158aa95a2c8aa30cc (#5691) 
⬆️ 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>
 2025-06-20 15:53:38 +02:00
Ettore Di Giacinto
79abe0ad77 Drop latest references to extras images 2025-06-20 15:51:16 +02:00
Ettore Di Giacinto
8131d11d1f Update quickstart.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-19 22:42:38 +02:00
LocalAI [bot]
beb01c91f3 docs: ⬆️ update docs version mudler/LocalAI (#5690) 
⬆️ 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>
 2025-06-19 22:13:16 +02:00
Ettore Di Giacinto
1ccd64ff6a chore: drop extras references from docs 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-19 22:04:28 +02:00
Ettore Di Giacinto
fc7681c68c Update README.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-19 21:46:09 +02:00
Ettore Di Giacinto
49d026a229 Update backends.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-06-19 19:47:09 +02:00
leopardracer
f9b968e19d Fix Typos and Improve Clarity in GPU Acceleration Documentation (#5688) 
Update GPU-acceleration.md

Signed-off-by: leopardracer <136604165+leopardracer@users.noreply.github.com>
v3.0.0 		2025-06-19 15:41:13 +02:00
LocalAI [bot]
022d4a5ecb chore: ⬆️ Update ggml-org/whisper.cpp to ecb8f3c2b4e282d5ef416516bcbfb92821f06bf6 (#5686) 
⬆️ 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>
 2025-06-19 08:23:42 +02:00
LocalAI [bot]
0e917eb01d chore: ⬆️ Update ggml-org/llama.cpp to 8d947136546773f6410756f37fcc5d3e65b8135d (#5685) 
⬆️ 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>
 2025-06-19 08:23:23 +02:00
Ettore Di Giacinto
efde0eaf83 feat(backend gallery): display download progress (#5687) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-06-18 23:49:44 +02:00
Maxim Evtush
add8fc35a2 Fix Typos in Documentation and Python Comments (#5658) 
* Update istftnet.py

Signed-off-by: Maxim Evtush <154841002+maximevtush@users.noreply.github.com>

* Update GPU-acceleration.md

Signed-off-by: Maxim Evtush <154841002+maximevtush@users.noreply.github.com>

---------

Signed-off-by: Maxim Evtush <154841002+maximevtush@users.noreply.github.com>
 2025-06-18 22:11:13 +02:00