Commit Graph

  • 03dddec538 chore(model gallery): add opengvlab_internvl3_5-8b (#6145) Ettore Di Giacinto 2025-08-26 17:49:31 +02:00
  • 3d34386712 chore(model gallery): add opengvlab_internvl3_5-14b (#6144) Ettore Di Giacinto 2025-08-26 17:17:49 +02:00
  • 1b3f66018b chore(model gallery): add opengvlab_internvl3_5-30b-a3b (#6143) Ettore Di Giacinto 2025-08-26 16:39:46 +02:00
  • 4381e892b8 Revert "CI tests" Ettore Di Giacinto 2025-08-26 15:26:23 +02:00
  • 3c3f477854 feat(mlx-audio): Add mlx-audio backend (#6138) Ettore Di Giacinto 2025-08-26 15:27:06 +02:00
  • f8a8cf3e95 feat(launcher): add LocalAI launcher app (#6127) Ettore Di Giacinto 2025-08-26 14:22:04 +02:00
  • 0fc88b3cdf chore: ⬆️ Update ggml-org/llama.cpp to c4e9239064a564de7b94ee2b401ae907235a8fca (#6139) LocalAI [bot] 2025-08-26 12:18:58 +02:00
  • 4993df81c3 fix(metal-llama.cpp): add all libutf8_validity Ettore Di Giacinto 2025-08-26 10:19:55 +02:00
  • 599bc88c6c fix(hipblas-llama.cpp): create symlink to libomp (#6140) Ettore Di Giacinto 2025-08-26 10:05:17 +02:00
  • 1a0d06f3db chore: ⬆️ Update ggml-org/llama.cpp to 043fb27d3808766d8ea8195bbd12359727264402 (#6137) LocalAI [bot] 2025-08-25 08:57:09 +02:00
  • 5e1a8b3621 chore: ⬆️ Update ggml-org/whisper.cpp to 7745fcf32846006128f16de429cfe1677c963b30 (#6136) LocalAI [bot] 2025-08-24 23:12:13 +02:00
  • 960e51e527 chore(diffusers): support both src and reference_images in diffusers (#6135) Ettore Di Giacinto 2025-08-24 22:03:08 +02:00
  • 195aa22e77 chore(docs): update list of supported backends (#6134) Ettore Di Giacinto 2025-08-24 20:09:19 +02:00
  • 478d2adfb7 Trigger CI feat/transformers-mps-cpu Ettore Di Giacinto 2025-08-24 16:48:33 +02:00
  • 909fdd1b0e feat(transformers): add support for CPU and MPS Ettore Di Giacinto 2025-08-24 16:47:51 +02:00
  • be132fe816 Revise latest project news in README Ettore Di Giacinto 2025-08-24 11:50:20 +02:00
  • ff5d2dc8be Revert "fix(rfdetr): use cpu torch for cpu builds" (#6131) Ettore Di Giacinto 2025-08-24 11:41:08 +02:00
  • c1cfa08226 chore(Dockerfile): drop python from images (#6130) Ettore Di Giacinto 2025-08-24 11:40:32 +02:00
  • fec8a36b36 fix(rfdetr): use cpu torch for cpu builds (#6129) Ettore Di Giacinto 2025-08-24 10:17:25 +02:00
  • 5d4f5d2355 feat(backends): add CPU variant for diffusers backend (#6128) Ettore Di Giacinto 2025-08-24 10:17:10 +02:00
  • 057248008f chore: ⬆️ Update ggml-org/llama.cpp to 710dfc465a68f7443b87d9f792cffba00ed739fe (#6126) LocalAI [bot] 2025-08-24 08:41:39 +02:00
  • 9f2c9cd691 feat(llama.cpp): Add gfx1201 support (#6125) Ettore Di Giacinto 2025-08-23 23:06:01 +02:00
  • 6971f71a6c Add mlx-vlm (#6119) Ettore Di Giacinto 2025-08-23 23:05:30 +02:00
  • 1ba66d00f5 feat: bundle python inside backends (#6123) Ettore Di Giacinto 2025-08-23 22:36:39 +02:00
  • 259383cf5e chore(deps): bump llama.cpp to '45363632cbd593537d541e81b600242e0b3d47fc' (#6122) Ettore Di Giacinto 2025-08-23 08:39:10 +02:00
  • 209c0694f5 Update backend.yml Ettore Di Giacinto 2025-08-22 23:36:24 +02:00
  • 0fd395d6ec feat(diffusers): add MPS version (#6121) Ettore Di Giacinto 2025-08-22 23:14:54 +02:00
  • d04bd47116 chore(Makefile): small fixup for darwin MLX builds Ettore Di Giacinto 2025-08-22 08:52:29 +02:00
  • 1d830ce7dd feat(mlx): add mlx backend (#6049) Ettore Di Giacinto 2025-08-22 08:42:29 +02:00
  • 6dccfb09f8 chore: ⬆️ Update ggml-org/llama.cpp to cd36b5e5c7fed2a3ac671dd542d579ca40b48b54 (#6118) LocalAI [bot] 2025-08-22 07:57:27 +02:00
  • e4d9cf8349 chore: ⬆️ Update ggml-org/llama.cpp to 7a6e91ad26160dd6dfb33d29ac441617422f28e7 (#6116) LocalAI [bot] 2025-08-20 23:05:39 +02:00
  • c899e90277 Update image-generation.md Ettore Di Giacinto 2025-08-20 10:37:11 +02:00
  • 8193d18c7c feat(img2img): Add support to Qwen Image Edit (#6113) Ettore Di Giacinto 2025-08-20 10:18:55 +02:00
  • 2e4dc6456f chore: ⬆️ Update ggml-org/llama.cpp to fb22dd07a639e81c7415e30b146f545f1a2f2caf (#6112) LocalAI [bot] 2025-08-20 09:01:36 +02:00
  • 4594430a3e feat(swagger): update swagger (#6111) LocalAI [bot] 2025-08-19 22:56:00 +02:00
  • 9c7f92c81f feat(p2p): automatically sync installed models between instances (#6108) Ettore Di Giacinto 2025-08-19 19:37:46 +02:00
  • 060037bcd4 Revert "chore(deps): bump transformers from 4.48.3 to 4.55.2 in /backend/python/coqui" (#6105) Ettore Di Giacinto 2025-08-19 15:00:33 +02:00
  • d9da4676b4 Revert "chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/coqui" (#6104) Ettore Di Giacinto 2025-08-19 15:00:11 +02:00
  • 5ef4c2e471 feat(diffusers): add torchvision to support qwen-image-edit (#6103) Ettore Di Giacinto 2025-08-19 12:05:48 +02:00
  • 27ce570844 chore(deps): bump transformers from 4.48.3 to 4.55.2 in /backend/python/coqui (#6096) dependabot[bot] 2025-08-19 09:44:01 +00:00
  • 42c7859ab1 chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/coqui (#6099) dependabot[bot] 2025-08-19 08:42:52 +00:00
  • e7e83d0fa6 Revert "chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/coqui" (#6102) Ettore Di Giacinto 2025-08-19 09:29:56 +02:00
  • c6dc1d86f1 chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/coqui (#6095) dependabot[bot] 2025-08-19 07:09:47 +00:00
  • 6fd2e1964d chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/coqui (#6097) dependabot[bot] 2025-08-19 08:11:58 +02:00
  • 49ae41b716 chore(deps): bump securego/gosec from 2.22.7 to 2.22.8 (#6098) dependabot[bot] 2025-08-19 08:11:26 +02:00
  • b3f0ed62fd chore(deps): bump actions/checkout from 4 to 5 (#6101) dependabot[bot] 2025-08-19 08:10:54 +02:00
  • 4b9afc418b chore: ⬆️ Update ggml-org/whisper.cpp to fc45bb86251f774ef817e89878bb4c2636c8a58f (#6089) LocalAI [bot] 2025-08-19 08:10:25 +02:00
  • e44ff8514b chore: ⬆️ Update ggml-org/llama.cpp to 6d7f1117e3e3285d0c5c11b5ebb0439e27920082 (#6088) LocalAI [bot] 2025-08-19 08:09:49 +02:00
  • 2b6be10b6b chore(deps): bump protobuf from 6.31.0 to 6.32.0 in /backend/python/transformers (#6100) dependabot[bot] 2025-08-19 05:09:17 +00:00
  • 1361d844a1 chore(model gallery): add lfm2-1.2b (#6092) Ettore Di Giacinto 2025-08-18 22:24:50 +02:00
  • fcc521cae5 chore(model gallery): add lfm2-vl-1.6b (#6091) Ettore Di Giacinto 2025-08-18 22:21:35 +02:00
  • 8cad7138be chore(model gallery): add lfm2-vl-450m (#6090) Ettore Di Giacinto 2025-08-18 22:17:03 +02:00
  • ebd1db2f09 chore(ci): Build modified backends on PR (#6086) Richard Palethorpe 2025-08-18 16:56:34 +01:00
  • 7920d75805 chore: ⬆️ Update ggml-org/llama.cpp to 21c17b5befc5f6be5992bc87fc1ba99d388561df (#6084) LocalAI [bot] 2025-08-18 10:26:58 +02:00
  • 1d0e24a865 chore(model gallery): add impish_longtail_12b (#6082) Ettore Di Giacinto 2025-08-17 09:41:01 +02:00
  • 9eed5ef872 chore: ⬆️ Update ggml-org/llama.cpp to 1fe00296f587dfca0957e006d146f5875b61e43d (#6079) LocalAI [bot] 2025-08-16 23:10:03 +02:00
  • 39ab80442a Tune the "dark gray" font color in the webui to make it more readable (#6078) Fabio Erculiani 2025-08-16 21:16:25 +02:00
  • 1b101df2c0 chore: InTrustedRoot -> VerifyPath Ettore Di Giacinto 2025-08-16 16:30:13 +02:00
  • 784bd5db33 chore(build): Use Purego with stablediffusion backend (#6067) Richard Palethorpe 2025-08-16 11:21:29 +01:00
  • b8b1ca782c chore(model gallery): add wingless_imp_8b-i1 (#6077) Ettore Di Giacinto 2025-08-16 08:45:38 +02:00
  • 1149fb66d3 chore(model gallery): add thedrummer_gemma-3-r1-4b-v1 (#6076) Ettore Di Giacinto 2025-08-16 08:39:10 +02:00
  • 243e86176e chore: ⬆️ Update ggml-org/llama.cpp to 5e6229a8409ac786e62cb133d09f1679a9aec13e (#6070) LocalAI [bot] 2025-08-16 08:38:57 +02:00
  • 8da38a0d10 chore(model gallery): add thedrummer_gemma-3-r1-12b-v1 (#6075) Ettore Di Giacinto 2025-08-16 08:35:49 +02:00
  • 60786fc876 chore(model gallery): add thedrummer_gemma-3-r1-27b-v1 (#6074) Ettore Di Giacinto 2025-08-16 08:31:42 +02:00
  • 9486b88a25 chore: ⬆️ Update ggml-org/whisper.cpp to 040510a132f0a9b51d4692b57a6abfd8c9660696 (#6069) LocalAI [bot] 2025-08-16 08:30:54 +02:00
  • bef4c10629 feat(ui): General improvements (#6072) Ettore Di Giacinto 2025-08-16 07:44:50 +02:00
  • 80f15851c5 chore(model-gallery): ⬆️ update checksum (#6071) LocalAI [bot] 2025-08-15 22:29:17 +02:00
  • 22067e3384 chore(rocm): bump rocm image, add gfx1200 support (#6065) Ettore Di Giacinto 2025-08-15 16:36:54 +02:00
  • 4fbd639463 chore(ci): fixup builds for darwin and hipblas Ettore Di Giacinto 2025-08-15 15:58:02 +02:00
  • 70f7d0c25f Revert "chore(build): Convert stablediffusion-ggml backend to Purego (#5989)" (#6064) Ettore Di Giacinto 2025-08-15 15:18:40 +02:00
  • 576e821298 chore(deps): bump llama.cpp to 'df36bce667bf14f8e538645547754386f9516326 (#6062) Ettore Di Giacinto 2025-08-15 13:28:15 +02:00
  • 7293f26fcf chore(ci): fix darwin image publish Ettore Di Giacinto 2025-08-15 08:51:44 +02:00
  • 79973a28ad chore(model gallery): add gemma-3-270m-it-qat (#6063) Ettore Di Giacinto 2025-08-15 08:41:38 +02:00
  • 8ab51509cc Update Makefile Ettore Di Giacinto 2025-08-15 08:33:25 +02:00
  • b3384e5428 Update Makefile Ettore Di Giacinto 2025-08-15 08:08:24 +02:00
  • 7050c9f69d feat(webui): add import/edit model page (#6050) Ettore Di Giacinto 2025-08-14 23:48:09 +02:00
  • 089efe05fd feat(backends): add system backend, refactor (#6059) Ettore Di Giacinto 2025-08-14 19:38:26 +02:00
  • 253b7537dc fix(llama-cpp/darwin): make sure to bundle libutf8 libs (#6060) Ettore Di Giacinto 2025-08-14 17:56:35 +02:00
  • 19c92c70c5 fix(backend-detection): default to CPU if there is less than 4GB of GPU available (#6057) Ettore Di Giacinto 2025-08-14 16:57:33 +02:00
  • b52bfaf1b3 fix: do not show invalid backends (#6058) Ettore Di Giacinto 2025-08-14 13:01:56 +02:00
  • bf60ca5bf0 Update Makefile Ettore Di Giacinto 2025-08-14 11:53:43 +02:00
  • 2b44467bd1 chore: ⬆️ Update ggml-org/llama.cpp to 29c8fbe4e05fd23c44950d0958299e25fbeabc5c (#6054) LocalAI [bot] 2025-08-14 09:19:15 +02:00
  • 8c1f4a131e chore: ⬆️ Update ggml-org/whisper.cpp to 16c2924cb2c4b5c9f79220aa7708eb5b346b029b (#6055) LocalAI [bot] 2025-08-13 23:08:22 +02:00
  • 10a3f0bd92 fix: chmod grpc processes only if needed (#6051) Ettore Di Giacinto 2025-08-13 12:08:53 +02:00
  • 72f4d541d0 chore: ⬆️ Update ggml-org/llama.cpp to f4586ee5986d6f965becb37876d6f3666478a961 (#6048) LocalAI [bot] 2025-08-13 08:33:48 +02:00
  • 9f812fdb84 chore: ⬆️ Update ggml-org/whisper.cpp to 5527454cdb3e15d7e2b8a6e2afcb58cb61651fd2 (#6047) LocalAI [bot] 2025-08-12 23:12:07 +02:00
  • b70ee45fff docs: ⬆️ update docs version mudler/LocalAI (#6046) LocalAI [bot] 2025-08-12 22:05:50 +02:00
  • 9d9c853541 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/transformers (#6013) dependabot[bot] 2025-08-12 22:05:16 +02:00
  • 18fcd8557c fix(llama.cpp): support gfx1200 (#6045) Ettore Di Giacinto 2025-08-12 22:04:30 +02:00
  • d8e27c38d7 chore(deps): bump oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu in /backend/python/common/template (#6016) dependabot[bot] 2025-08-12 18:57:20 +00:00
  • 3b0dc87932 chore(deps): bump torch from 2.3.1+cxx11.abi to 2.8.0 in /backend/python/common/template (#6025) dependabot[bot] 2025-08-12 17:58:33 +00:00
  • 2374485222 chore(deps): bump actions/download-artifact from 4 to 5 (#6015) dependabot[bot] 2025-08-12 18:54:57 +02:00
  • 0ca1765c17 chore(deps): bump actions/checkout from 4 to 5 (#6014) dependabot[bot] 2025-08-12 18:54:39 +02:00
  • 90b5ed9a1e chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/common/template (#6034) dependabot[bot] 2025-08-12 18:44:33 +02:00
  • d438b769da chore(deps): bump intel-extension-for-pytorch from 2.3.110+xpu to 2.8.10+xpu in /backend/python/bark (#6043) dependabot[bot] 2025-08-12 18:44:05 +02:00
  • 2e4bd1e33d chore(deps): bump oneccl-bind-pt from 2.3.100+xpu to 2.8.0+xpu in /backend/python/rerankers (#6021) dependabot[bot] 2025-08-12 16:04:54 +00:00
  • ff73800970 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/exllama2 (#6019) dependabot[bot] 2025-08-12 16:42:46 +02:00
  • 94cb20ae7f chore(build): Convert stablediffusion-ggml backend to Purego (#5989) Richard Palethorpe 2025-08-12 15:42:15 +01:00
  • 47c20f9adb chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/rerankers (#6022) dependabot[bot] 2025-08-12 15:24:48 +02:00
  • a7fe153630 chore(deps): bump grpcio from 1.71.0 to 1.74.0 in /backend/python/bark (#6033) dependabot[bot] 2025-08-12 15:16:00 +02:00