dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21
3841 commits 54 branches 113 tags 41 MiB
Commit graph

3841 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ettore Di Giacinto
0bb33fab55
chore(model gallery): add ibm-granite_granite-3.3-2b-instruct (#5205) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-18 10:15:05 +02:00
Ettore Di Giacinto
e3bf7f77f7
chore(model gallery): add ibm-granite_granite-3.3-8b-instruct (#5204) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-18 09:59:17 +02:00
LocalAI [bot]
bd1707d339
chore: ⬆️ Update ggml-org/llama.cpp to 2f74c354c0f752ed9aabf7d3a350e6edebd7e744 (#5203) 
⬆️ 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>
 2025-04-17 21:52:12 +00:00
Ettore Di Giacinto
0474804541 fix(ci): remove duplicate entry 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-17 19:51:21 +02:00
Ettore Di Giacinto
72693b3917
feat(install.sh): allow to uninstall with --uninstall (#5202) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-17 16:32:23 +02:00
Florian Bachmann
a03b70010f
fix(talk): Talk interface sends content-type headers to chatgpt (#5200) 
Talk interface sends content-type headers to chatgpt

Signed-off-by: baflo <834350+baflo@users.noreply.github.com>
 2025-04-17 15:02:11 +02:00
Ettore Di Giacinto
e3717e5c1a
chore(model gallery): add qwen2.5-14b-instruct-1m (#5201) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-17 10:42:22 +02:00
Ettore Di Giacinto
c8f6858218
chore(ci): add latest images for core (#5198) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-17 10:00:18 +02:00
Ettore Di Giacinto
06d7cc43ae
chore(model gallery): add dreamgen_lucid-v1-nemo (#5196) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-17 09:10:09 +02:00
Ettore Di Giacinto
f2147cb850
chore(model gallery): add thedrummer_rivermind-12b-v1 (#5195) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-17 09:02:54 +02:00
Ettore Di Giacinto
75bb9f4c28
chore(model gallery): add menlo_rezero-v0.1-llama-3.2-3b-it-grpo-250404 (#5194) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-17 09:00:11 +02:00
LocalAI [bot]
a2ef4b1e07
chore: ⬆️ Update ggml-org/llama.cpp to 015022bb53387baa8b23817ac03743705c7d472b (#5192) 
⬆️ 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>
 2025-04-17 08:04:37 +02:00
LocalAI [bot]
161c9fe2db
docs: ⬆️ update docs version mudler/LocalAI (#5191) 
⬆️ 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>
 2025-04-16 22:13:49 +02:00
Ettore Di Giacinto
7547463f81
Update quickstart.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-04-16 08:48:55 +02:00
Gianluca Boiano
32e4dfd47b
chore(model gallery): add suno-ai bark-cpp model (#5187) 
Signed-off-by: Gianluca Boiano <morf3089@gmail.com>
 2025-04-16 08:22:46 +02:00
Gianluca Boiano
f67e5dec68
fix: bark-cpp: assign FLAG_TTS to bark-cpp backend (#5186) 
Signed-off-by: Gianluca Boiano <morf3089@gmail.com>
 2025-04-16 08:21:30 +02:00
LocalAI [bot]
297d54acea
chore: ⬆️ Update ggml-org/llama.cpp to 80f19b41869728eeb6a26569957b92a773a2b2c6 (#5183) 
⬆️ 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>
 2025-04-15 22:50:32 +00:00
Ettore Di Giacinto
56f44d448c chore(docs): decrease logo size, minor enhancements 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-15 22:00:51 +02:00
Richard Palethorpe
0f0fafacd9
fix(stablediffusion): Avoid overwriting SYCL specific flags from outer make call (#5181) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-04-15 19:31:25 +02:00
Ettore Di Giacinto
4f239bac89
feat: rebrand - LocalAGI and LocalRecall joins the LocalAI stack family (#5159) 
* wip

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

* docs

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

* Update lotusdocs and hugo

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

* rephrasing

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

* fixups

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

* Latest fixups

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

* Adjust readme section

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-15 17:51:24 +02:00
Ettore Di Giacinto
04d74ac648
chore(model gallery): add m1-32b (#5182) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-15 17:17:17 +02:00
Richard Palethorpe
18c3dc33ee
fix(stablediffusion): Pass ROCM LD CGO flags through to recursive make (#5179) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-04-15 09:27:29 +02:00
LocalAI [bot]
508cfa7369
chore: ⬆️ Update ggml-org/llama.cpp to d6d2c2ab8c8865784ba9fef37f2b2de3f2134d33 (#5178) 
⬆️ 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>
 2025-04-14 23:10:16 +02:00
Ettore Di Giacinto
1f94cddbae
chore(model gallery): add nvidia_llama-3.1-8b-ultralong-4m-instruct (#5177) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-14 12:30:55 +02:00
Ettore Di Giacinto
21ae7b4cd4
chore(model gallery): add nvidia_llama-3.1-8b-ultralong-1m-instruct (#5176) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-14 12:28:09 +02:00
Ettore Di Giacinto
bef22ab547
chore(model gallery): add skywork_skywork-or1-32b-preview (#5175) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-14 12:25:43 +02:00
Ettore Di Giacinto
eb04e8cdcf
chore(model gallery): add skywork_skywork-or1-math-7b (#5174) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-14 12:23:44 +02:00
Ettore Di Giacinto
17e533a086
chore(model gallery): add skywork_skywork-or1-7b-preview (#5173) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-14 12:20:20 +02:00
qwerty108109
4fc68409ff
Update README.md (#5172) 
Modified the README.md to separate out the different docker run commands to make it easier to copy into the terminal.

Signed-off-by: qwerty108109 <97707491+qwerty108109@users.noreply.github.com>
 2025-04-14 10:48:10 +02:00
Richard Palethorpe
e587044449
fix(stablediffusion): Avoid GGML commit which causes CUDA compile error (#5170) 
Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-04-14 09:29:09 +02:00
LocalAI [bot]
1f09db5161
chore: ⬆️ Update ggml-org/llama.cpp to 71e90e8813f90097701e62f7fce137d96ddf41e2 (#5171) 
⬆️ 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>
 2025-04-13 21:46:07 +00:00
Ettore Di Giacinto
05b744f086
chore(model gallery): add daichi-12b (#5169) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-13 15:53:11 +02:00
Ettore Di Giacinto
89ca4bc02d
chore(model gallery): add hamanasu-magnum-4b-i1 (#5168) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-13 14:37:59 +02:00
Ettore Di Giacinto
e626aa48a4
chore(model gallery): add hamanasu-adventure-4b-i1 (#5167) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-13 14:35:57 +02:00
Ettore Di Giacinto
752b5e0339
chore(model gallery): add mag-picaro-72b (#5166) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-13 14:34:14 +02:00
Ettore Di Giacinto
637d72d6e3
chore(model gallery): add lightthinker-qwen (#5165) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-13 14:31:05 +02:00
LocalAI [bot]
f3bfec580a
chore: ⬆️ Update ggml-org/llama.cpp to bc091a4dc585af25c438c8473285a8cfec5c7695 (#5158) 
⬆️ 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>
 2025-04-13 08:23:41 +00:00
Ettore Di Giacinto
165c1ddff3
chore(model gallery): add tesslate_gradience-t1-3b-preview (#5160) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-12 10:37:40 +02:00
Ettore Di Giacinto
fb83238e9e
chore(model gallery): add zyphra_zr1-1.5b (#5157) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-11 10:06:05 +02:00
Ettore Di Giacinto
700bfa41c7
chore(model gallery): add agentica-org_deepcoder-1.5b-preview (#5156) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-11 10:03:59 +02:00
LocalAI [bot]
25bdc350df
chore: ⬆️ Update ggml-org/llama.cpp to 64eda5deb9859e87a020e56bab5d2f9ca956f1de (#5155) 
⬆️ 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>
 2025-04-10 21:44:55 +00:00
Richard Palethorpe
1b899e1a68
feat(stablediffusion): Enable SYCL (#5144) 
* feat(sycl): Enable SYCL for stable diffusion

This is a pain because we compile with CGO, but SD is compiled with
CMake. I don't think we can easily use CMake to set the linker flags
necessary. Also I could not find pkg-config calls that would fully set
the flags, so some of them are set manually.

See https://www.intel.com/content/www/us/en/developer/tools/oneapi/onemkl-link-line-advisor.html
for reference. I also resorted to searching the shared object files in
MKLROOT/lib for the symbols.

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

* fix(ci): Don't set nproc on cmake

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

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
 2025-04-10 15:20:53 +02:00
Ettore Di Giacinto
3bf13f8c69
chore(model gallery): add soob3123_amoral-cogito-v1-preview-qwen-14b (#5154) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-10 10:07:56 +02:00
Ettore Di Giacinto
7a00729374
chore(model gallery): add trappu_magnum-picaro-0.7-v2-12b (#5153) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-10 10:03:42 +02:00
Ettore Di Giacinto
d484028532
feat(diffusers): add support for Lumina2Text2ImgPipeline (#4806) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-10 09:55:51 +02:00
LocalAI [bot]
0eb7fc2c41
chore: ⬆️ Update ggml-org/llama.cpp to d3bd7193ba66c15963fd1c59448f22019a8caf6e (#5152) 
⬆️ 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>
 2025-04-09 22:01:25 +00:00
Ettore Di Giacinto
a69e30e0c9
chore(model gallery): add agentica-org_deepcoder-14b-preview (#5151) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-09 16:55:47 +02:00
Ettore Di Giacinto
9c018e6bff
chore(model gallery): add deepcogito_cogito-v1-preview-llama-70b (#5150) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-09 16:54:59 +02:00
Ettore Di Giacinto
281e818047
chore(model gallery): add deepcogito_cogito-v1-preview-llama-70b (#5150) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-09 16:53:28 +02:00
Ettore Di Giacinto
270f0e2157
chore(model gallery): add deepcogito_cogito-v1-preview-qwen-32b (#5149) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-04-09 16:48:15 +02:00