Commit Graph

  • 5433f1a70e
    chore: ⬆️ Update ggml-org/llama.cpp to f05a6d71a0f3dbf0730b56a1abbad41c0f42e63d (#5340) master LocalAI [bot] 2025-05-09 01:13:28 +02:00
  • fc84386b86 adjust cublas for whisper.cpp deps/whisper.cpp Ettore Di Giacinto 2025-05-08 22:02:00 +02:00
  • 29bf6a6b4a Fixups macOS arm64 Ettore Di Giacinto 2025-05-08 19:29:00 +02:00
  • 01aa00237f add libggml-metal Ettore Di Giacinto 2025-05-08 15:52:29 +02:00
  • 62e720e638 chore(deps): bump whisper.cpp Ettore Di Giacinto 2025-05-08 12:30:38 +02:00
  • d5e032bdcd
    chore(model gallery): add gemma-3-12b-fornaxv.2-qat-cot (#5337) Ettore Di Giacinto 2025-05-08 12:07:25 +02:00
  • de786f6586
    chore(model gallery): add symiotic-14b-i1 (#5336) Ettore Di Giacinto 2025-05-08 12:03:35 +02:00
  • 8b9bc4aa6e
    chore(model gallery): add qwen3-14b-uncensored (#5335) Ettore Di Giacinto 2025-05-08 11:59:26 +02:00
  • e6cea7d28e
    chore(model gallery): add cognition-ai_kevin-32b (#5334) Ettore Di Giacinto 2025-05-08 11:57:12 +02:00
  • 7d7d56f2ce
    chore(model gallery): add servicenow-ai_apriel-nemotron-15b-thinker (#5333) Ettore Di Giacinto 2025-05-08 11:55:35 +02:00
  • 1caae91ab6
    chore(model gallery): add qwen3-4b-esper3-i1 (#5332) Ettore Di Giacinto 2025-05-08 11:52:02 +02:00
  • e90f2cb0ca
    chore: ⬆️ Update ggml-org/llama.cpp to 814f795e063c257f33b921eab4073484238a151a (#5331) LocalAI [bot] 2025-05-08 09:25:13 +02:00
  • 5a4291fadd
    docs: update README badges Ettore Di Giacinto 2025-05-07 22:20:06 +02:00
  • 91ef58ee5a
    chore(model gallery): add qwen3-14b-griffon-i1 (#5330) Ettore Di Giacinto 2025-05-07 11:07:38 +02:00
  • a86e8c78f1
    chore: ⬆️ Update ggml-org/llama.cpp to 91a86a6f354aa73a7aab7bc3d283be410fdc93a5 (#5329) LocalAI [bot] 2025-05-07 01:39:10 +02:00
  • adb24214c6
    chore(deps): bump llama.cpp to b34c859146630dff136943abc9852ca173a7c9d6 (#5323) Ettore Di Giacinto 2025-05-06 11:21:25 +02:00
  • f03a0430aa
    chore(model gallery): add claria-14b (#5326) Ettore Di Giacinto 2025-05-06 10:48:03 +02:00
  • 73bc12abc0
    chore(model gallery): add goekdeniz-guelmez_josiefied-qwen3-8b-abliterated-v1 (#5325) Ettore Di Giacinto 2025-05-06 10:38:20 +02:00
  • 7fa437bbcc
    chore(model gallery): add huihui-ai_qwen3-14b-abliterated (#5324) Ettore Di Giacinto 2025-05-06 10:35:55 +02:00
  • 4a27c99928
    chore(model-gallery): ⬆️ update checksum (#5321) LocalAI [bot] 2025-05-06 10:01:28 +02:00
  • 6ce94834b6
    fix(hipblas): do not build all cpu-specific flags (#5322) Ettore Di Giacinto 2025-05-06 10:00:50 +02:00
  • 84a26458dc
    chore(deps): bump mxschmitt/action-tmate from 3.21 to 3.22 (#5319) dependabot[bot] 2025-05-05 22:17:59 +00:00
  • 7aa377b6a9
    fix(arm64): do not build instructions which are not available (#5318) Ettore Di Giacinto 2025-05-05 17:30:00 +02:00
  • 64e66dda4a
    chore(model gallery): add allura-org_remnant-qwen3-8b (#5317) Ettore Di Giacinto 2025-05-05 11:09:07 +02:00
  • a085f61fdc
    chore: ⬆️ Update ggml-org/llama.cpp to 9fdfcdaeddd1ef57c6d041b89cd8fb7048a0f028 (#5316) LocalAI [bot] 2025-05-05 01:00:25 +02:00
  • 21bdfe5fa4
    fix: use rice when embedding large binaries (#5309) Ettore Di Giacinto 2025-05-04 16:42:42 +02:00
  • 7ebd7b2454
    chore(model gallery): add rei-v3-kto-12b (#5313) Ettore Di Giacinto 2025-05-04 09:41:35 +02:00
  • 6984749ea1
    chore(model gallery): add kalomaze_qwen3-16b-a3b (#5312) Ettore Di Giacinto 2025-05-04 09:39:38 +02:00
  • c0a206bc7a
    chore(model gallery): add qwen3-30b-a1.5b-high-speed (#5311) Ettore Di Giacinto 2025-05-04 09:38:01 +02:00
  • 01bbb31fb3
    chore: ⬆️ Update ggml-org/llama.cpp to 36667c8edcded08063ed51c7d57e9e086bbfc903 (#5300) LocalAI [bot] 2025-05-04 09:23:01 +02:00
  • 72111c597d
    fix(gpu): do not assume gpu being returned has node and mem (#5310) Ettore Di Giacinto 2025-05-03 19:00:24 +02:00
  • b2f9fc870b
    chore(defaults): enlarge defaults, drop gpu layers which is infered (#5308) Ettore Di Giacinto 2025-05-03 18:44:51 +02:00
  • 1fc6d469ac
    chore(deps): bump llama.cpp to '1d36b3670b285e69e58b9d687c770a2a0a192194 (#5307) Ettore Di Giacinto 2025-05-03 18:44:40 +02:00
  • 05848b2027
    chore(model gallery): add smoothie-qwen3-8b (#5306) Ettore Di Giacinto 2025-05-03 10:35:20 +02:00
  • 1da0644aa3
    chore(model gallery): add qwen-3-32b-medical-reasoning-i1 (#5305) Ettore Di Giacinto 2025-05-03 10:24:07 +02:00
  • c087cd1377
    chore(model gallery): add amoral-qwen3-14b (#5304) Ettore Di Giacinto 2025-05-03 10:21:48 +02:00
  • c621412f6a
    chore(model gallery): add comet_12b_v.5-i1 (#5303) Ettore Di Giacinto 2025-05-03 10:20:03 +02:00
  • 5a8b1892cd
    chore(model gallery): add genericrpv3-4b (#5302) Ettore Di Giacinto 2025-05-03 10:18:31 +02:00
  • 5b20426863
    chore(model gallery): add planetoid_27b_v.2 (#5301) Ettore Di Giacinto 2025-05-03 10:14:33 +02:00
  • 5c6cd50ed6
    feat(llama.cpp): estimate vram usage (#5299) Ettore Di Giacinto 2025-05-02 17:40:26 +02:00
  • bace6516f1
    chore(model gallery): add webthinker-qwq-32b-i1 (#5298) Ettore Di Giacinto 2025-05-02 09:57:49 +02:00
  • 3baadf6f27
    chore(model gallery): add shuttleai_shuttle-3.5 (#5297) Ettore Di Giacinto 2025-05-02 09:48:11 +02:00
  • 8804c701b8
    chore(model gallery): add microsoft_phi-4-reasoning (#5296) Ettore Di Giacinto 2025-05-02 09:46:20 +02:00
  • 7b3ceb19bb
    chore(model gallery): add microsoft_phi-4-reasoning-plus (#5295) Ettore Di Giacinto 2025-05-02 09:43:38 +02:00
  • e7f3effea1
    chore(model gallery): add furina-8b (#5294) Ettore Di Giacinto 2025-05-02 09:39:22 +02:00
  • 61694a2ffb
    chore(model gallery): add josiefied-qwen3-8b-abliterated-v1 (#5293) Ettore Di Giacinto 2025-05-02 09:36:35 +02:00
  • 573a3f104c
    chore: ⬆️ Update ggml-org/llama.cpp to d7a14c42a1883a34a6553cbfe30da1e1b84dfd6a (#5292) LocalAI [bot] 2025-05-02 09:21:38 +02:00
  • 0e8af53a5b chore: update quickstart Ettore Di Giacinto 2025-05-01 22:36:33 +02:00
  • 960ffa808c
    chore(model gallery): add microsoft_phi-4-mini-reasoning (#5288) Ettore Di Giacinto 2025-05-01 10:17:58 +02:00
  • 92719568e5
    chore(model gallery): add fast-math-qwen3-14b (#5287) Ettore Di Giacinto 2025-05-01 10:14:51 +02:00
  • 163939af71
    chore(model gallery): add qwen3-8b-jailbroken (#5286) Ettore Di Giacinto 2025-05-01 10:13:01 +02:00
  • 399f1241dc
    chore(model gallery): add qwen3-30b-a3b-abliterated (#5285) Ettore Di Giacinto 2025-05-01 10:07:42 +02:00
  • 58c9ade2e8
    chore: ⬆️ Update ggml-org/llama.cpp to 3e168bede4d27b35656ab8026015b87659ecbec2 (#5284) LocalAI [bot] 2025-05-01 10:01:39 +02:00
  • 6e1c93d84f
    fix(ci): comment out vllm tests Ettore Di Giacinto 2025-05-01 10:01:22 +02:00
  • 4076ea0494
    fix: vllm missing logprobs (#5279) Wyatt Neal 2025-04-30 08:55:07 -04:00
  • 26cbf77c0d
    chore(model gallery): add mlabonne_qwen3-4b-abliterated (#5283) Ettore Di Giacinto 2025-04-30 11:09:58 +02:00
  • 640790d628
    chore(model gallery): add mlabonne_qwen3-8b-abliterated (#5282) Ettore Di Giacinto 2025-04-30 11:08:26 +02:00
  • 4132adea2f
    chore(model gallery): add mlabonne_qwen3-14b-abliterated (#5281) Ettore Di Giacinto 2025-04-30 11:04:49 +02:00
  • 2b2d907a3a
    chore: ⬆️ Update ggml-org/llama.cpp to e2e1ddb93a01ce282e304431b37e60b3cddb6114 (#5278) LocalAI [bot] 2025-04-29 23:46:08 +02:00
  • 6e8f4f584b
    fix(diffusers): consider options only in form of key/value (#5277) Ettore Di Giacinto 2025-04-29 17:08:55 +02:00
  • 662cfc2b48
    fix(aio): Fix copypasta in download files for gpt-4 model (#5276) Richard Palethorpe 2025-04-29 16:08:16 +01:00
  • a25d355d66
    chore(model gallery): add qwen3-0.6b (#5275) Ettore Di Giacinto 2025-04-29 10:10:16 +02:00
  • 6d1cfdbefc
    chore(model gallery): add qwen3-1.7b (#5274) Ettore Di Giacinto 2025-04-29 10:06:03 +02:00
  • 5ecc478968
    chore(model gallery): add qwen3-4b (#5273) Ettore Di Giacinto 2025-04-29 10:01:22 +02:00
  • aef5c4291b
    chore(model gallery): add qwen3-8b (#5272) Ettore Di Giacinto 2025-04-29 09:59:17 +02:00
  • c059f912b9
    chore(model gallery): add qwen3-14b (#5271) Ettore Di Giacinto 2025-04-29 09:56:50 +02:00
  • bc1e059259
    chore: ⬆️ Update ggml-org/llama.cpp to 5f5e39e1ba5dbea814e41f2a15e035d749a520bc (#5267) LocalAI [bot] 2025-04-29 09:49:42 +02:00
  • 38dc07793a
    chore(model-gallery): ⬆️ update checksum (#5268) LocalAI [bot] 2025-04-29 09:49:23 +02:00
  • da6ef0967d
    chore(model gallery): add qwen3-32b (#5270) Ettore Di Giacinto 2025-04-29 09:48:28 +02:00
  • 7a011e60bd
    chore(model gallery): add qwen3-30b-a3b (#5269) Ettore Di Giacinto 2025-04-29 09:44:44 +02:00
  • e13dd5b09f
    chore(deps): bump appleboy/scp-action from 0.1.7 to 1.0.0 (#5265) dependabot[bot] 2025-04-28 22:36:30 +00:00
  • b652cbc3d2
    chore(deps): bump torch in /backend/python/exllama2 dependabot/pip/backend/python/exllama2/torch-2.7.0cu118 dependabot[bot] 2025-04-28 19:21:45 +00:00
  • 86ee303bd6
    chore(model gallery): add nvidia_openmath-nemotron-14b-kaggle (#5264) Ettore Di Giacinto 2025-04-28 19:52:36 +02:00
  • 978ee96fd3
    chore(model gallery): add nvidia_openmath-nemotron-14b (#5263) Ettore Di Giacinto 2025-04-28 19:43:49 +02:00
  • 3ad5691db6
    chore(model gallery): add nvidia_openmath-nemotron-7b (#5262) Ettore Di Giacinto 2025-04-28 19:41:59 +02:00
  • 0027681090
    chore(model gallery): add nvidia_openmath-nemotron-1.5b (#5261) Ettore Di Giacinto 2025-04-28 19:40:09 +02:00
  • 8cba990edc
    chore(model gallery): add nvidia_openmath-nemotron-32b (#5260) Ettore Di Giacinto 2025-04-28 19:36:57 +02:00
  • 88857696d4
    fix(CUDA): Add note for how to run CUDA with SELinux (#5259) Simon Redman 2025-04-28 03:00:52 -04:00
  • 23f347e687
    chore: ⬆️ Update ggml-org/llama.cpp to ced44be34290fab450f8344efa047d8a08e723b4 (#5258) LocalAI [bot] 2025-04-27 23:59:35 +02:00
  • b6e3dc5f02
    docs: update docs for DisableWebUI flag (#5256) Mohit Gaur 2025-04-27 19:32:02 +05:30
  • 69667521e2
    fix(install/gpu):Fix docker not being able to leverage the GPU on systems that have SELinux Enforced (#5252) Alessandro Pirastru 2025-04-27 16:01:29 +02:00
  • 2a92effc5d
    chore: ⬆️ Update ggml-org/llama.cpp to 77d5e9a76a7b4a8a7c5bf9cf6ebef91860123cba (#5254) LocalAI [bot] 2025-04-27 09:21:02 +02:00
  • a65e012aa2
    docs(Vulkan): Add GPU docker documentation for Vulkan (#5255) Simon Redman 2025-04-27 03:20:26 -04:00
  • 8e9b41d05f
    chore(ci): build only images with ffmpeg included, simplify tags (#5251) Ettore Di Giacinto 2025-04-27 08:23:25 +02:00
  • 078da5c2f0
    feat(swagger): update swagger (#5253) LocalAI [bot] 2025-04-27 00:40:35 +02:00
  • c5af5d139c
    Update index.yaml Ettore Di Giacinto 2025-04-26 18:42:22 +02:00
  • 2c9279a542
    feat(video-gen): add endpoint for video generation (#5247) Ettore Di Giacinto 2025-04-26 18:05:01 +02:00
  • a67d22f5f2 chore(model gallery): add mmproj to gemma3 models (now working) Ettore Di Giacinto 2025-04-26 17:31:40 +02:00
  • dc7c51dcc7 chore(model gallery): fix correct filename for gemma-3-27b-it-qat Ettore Di Giacinto 2025-04-26 17:27:50 +02:00
  • 98df65c7aa
    chore(model gallery): add l3.3-genetic-lemonade-sunset-70b (#5250) Ettore Di Giacinto 2025-04-26 17:19:20 +02:00
  • 1559b6b522
    chore(model gallery): add l3.3-geneticlemonade-unleashed-v2-70b (#5249) Ettore Di Giacinto 2025-04-26 17:17:18 +02:00
  • a0244e3fb4
    feat(install): added complete process for installing nvidia drivers on fedora without pulling X11 (#5246) Alessandro Pirastru 2025-04-26 09:44:40 +02:00
  • d66396201a
    chore: ⬆️ Update ggml-org/llama.cpp to 295354ea6848a77bdee204ee1c971d9b92ffcca9 (#5245) LocalAI [bot] 2025-04-26 00:05:16 +02:00
  • 9628860c0e
    feat(llama.cpp/clip): inject gpu options if we detect GPUs (#5243) Ettore Di Giacinto 2025-04-26 00:04:47 +02:00
  • e747d984b3
    chore(deps): bump torch in /backend/python/exllama2 in the pip group dependabot/pip/backend/python/exllama2/pip-70d2b8ed4b dependabot[bot] 2025-04-25 19:33:45 +00:00
  • cae9bf1308
    chore(deps): bump grpcio to 1.72.0 (#5244) Ettore Di Giacinto 2025-04-25 21:32:37 +02:00
  • 5bb5da0760
    fix(ci): add clang (#5242) Ettore Di Giacinto 2025-04-25 16:20:05 +02:00
  • 867973a850
    chore(model gallery): add soob3123_veritas-12b (#5241) Ettore Di Giacinto 2025-04-25 09:20:01 +02:00
  • 701cd6b6d5
    chore: ⬆️ Update ggml-org/llama.cpp to 226251ed56b85190e18a1cca963c45b888f4953c (#5240) LocalAI [bot] 2025-04-25 08:42:22 +02:00
  • 7f61d397d5
    fix(stablediffusion-ggml): Build with DSD CUDA, HIP and Metal flags (#5236) Richard Palethorpe 2025-04-24 09:27:17 +01:00