Commit Graph

  • 53276d28e7 feat(musicgen): add ace-step and UI interface (#8396) Ettore Di Giacinto 2026-02-05 12:04:53 +01:00
  • 6dbcdb0b9e fix: filter GGUF and GGML files from model list (#8397) Yaroslav98214 2026-02-05 10:17:46 +01:00
  • c30866ba95 chore: ⬆️ Update ggml-org/llama.cpp to b536eb023368701fe3564210440e2df6151c3e65 (#8399) LocalAI [bot] 2026-02-04 23:08:08 +01:00
  • b413beba2d chore: ⬆️ Update ggml-org/whisper.cpp to 941bdabbe4561bc6de68981aea01bc5ab05781c5 (#8398) LocalAI [bot] 2026-02-04 22:20:59 +01:00
  • 9db4df22f3 chore: update torch and torchaudio version specifications for qwen-tts in MPS Ettore Di Giacinto 2026-02-04 16:55:42 +01:00
  • 5ac50c9348 fix(docs): Promote DEBUG=false in production docker compose (#8390) Jonas Bernard 2026-02-04 09:35:32 +01:00
  • 5201b58d3e feat(mlx): Add support for CUDA12, CUDA13, L4T, SBSA and CPU (#8380) Ettore Di Giacinto 2026-02-03 23:53:34 +01:00
  • 8fa6737bdc chore(model gallery): 🤖 add 1 new models via gallery agent (#8381) LocalAI [bot] 2026-02-03 22:40:22 +01:00
  • 3039ced287 chore(ci): enlarge sleep startup time Ettore Di Giacinto 2026-02-03 22:07:07 +01:00
  • e7fc604dbc feat(metal): try to extend support to remaining backends (#8374) Ettore Di Giacinto 2026-02-03 21:57:50 +01:00
  • 5195062e12 fix(realtime): Include noAction function in prompt template and handle tool_choice (#8372) Richard Palethorpe 2026-02-03 13:30:37 +00:00
  • 6a1e44c8ff Fix markdown parsing to handle multi-line constructs correctly copilot/fix-chat-interface-markdown-again copilot-swe-agent[bot] 2026-02-03 11:42:51 +00:00
  • bda40b266c Initial plan copilot-swe-agent[bot] 2026-02-03 11:40:19 +00:00
  • c86edf06f2 chore(deps): bump github.com/onsi/gomega from 1.39.0 to 1.39.1 (#8357) dependabot[bot] 2026-02-03 09:00:59 +01:00
  • 5d14c2fe4d chore(deps): bump sentence-transformers from 5.2.0 to 5.2.2 in /backend/python/transformers (#8358) dependabot[bot] 2026-02-03 08:37:05 +01:00
  • 4601143998 chore(deps): bump go.opentelemetry.io/otel/exporters/prometheus from 0.61.0 to 0.62.0 (#8359) dependabot[bot] 2026-02-03 08:36:34 +01:00
  • 7913ea2bfb chore(deps): bump go.opentelemetry.io/otel/sdk/metric from 1.39.0 to 1.40.0 (#8354) dependabot[bot] 2026-02-03 08:36:10 +01:00
  • d6409bd2eb Revert "chore(deps): bump torch from 2.7.0 to 2.7.1+xpu in /backend/python/vllm in the pip group across 1 directory" (#8367) Ettore Di Giacinto 2026-02-03 08:34:54 +01:00
  • 98872791e5 chore(deps): bump protobuf from 6.33.4 to 6.33.5 in /backend/python/transformers (#8356) dependabot[bot] 2026-02-03 08:33:45 +01:00
  • c6d47cb4e5 chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.19.0 to 1.20.0 (#8355) dependabot[bot] 2026-02-03 08:33:24 +01:00
  • f754a8edb1 chore(deps): bump go.opentelemetry.io/otel/metric from 1.39.0 to 1.40.0 (#8353) dependabot[bot] 2026-02-03 08:33:04 +01:00
  • 4c0e70086d chore(deps): bump torch from 2.7.0 to 2.7.1+xpu in /backend/python/vllm in the pip group across 1 directory (#8360) dependabot[bot] 2026-02-03 03:07:02 +00:00
  • f8bd527dfe chore(deps): bump appleboy/ssh-action from 1.2.4 to 1.2.5 (#8352) dependabot[bot] 2026-02-03 01:53:20 +00:00
  • 5041294265 Initial plan copilot/fix-chat-interface-rendering-issues copilot-swe-agent[bot] 2026-02-02 22:01:37 +00:00
  • 805654fa23 Initial plan copilot/fix-chat-interface-markdown copilot-swe-agent[bot] 2026-02-02 21:38:30 +00:00
  • 4b0dbe8ae0 Initial plan copilot/fix-chat-interface-markdown-issues copilot-swe-agent[bot] 2026-02-02 21:21:41 +00:00
  • 08b2b8d755 fix(libbackend): do not inject --index-strategy unsafe-best-match to all Ettore Di Giacinto 2026-02-02 17:13:45 +01:00
  • 10a1e6c74d feat(whisperx): add whisperx backend for transcription with speaker diarization (#8299) Dream 2026-02-02 10:33:12 -05:00
  • b7585ca738 fix(api): Add missing field in initial OpenAI streaming response (#8341) Alex O'Connell 2026-02-02 02:30:04 -05:00
  • 8cae99229c chore: ⬆️ Update ggml-org/llama.cpp to 2634ed207a17db1a54bd8df0555bd8499a6ab691 (#8336) LocalAI [bot] 2026-02-01 22:23:57 +01:00
  • 04e0f444e1 chore(model gallery): Add Qwen 3 VL 8B thinking & instruct (#8329) rampa3 2026-02-01 17:34:31 +01:00
  • 6f410f4cbe chore(model gallery): Rename downloaded filename for Magistral Small mmproj (#8327) rampa3 2026-02-01 17:33:48 +01:00
  • 800f749c7b fix: drop gguf VRAM estimation (now redundant) (#8325) Ettore Di Giacinto 2026-02-01 17:33:28 +01:00
  • b6459ddd57 feat(api): Add transcribe response format request parameter & adjust STT backends (#8318) Andres 2026-02-01 17:33:17 +01:00
  • 397f7f0862 fix(ui): take account of reasoning in token count calculation (#8324) Ettore Di Giacinto 2026-02-01 10:48:31 +01:00
  • 234072769c chore(model gallery): 🤖 add 1 new models via gallery agent (#8321) LocalAI [bot] 2026-02-01 09:02:05 +01:00
  • 3445415b3d chore: ⬆️ Update ggml-org/llama.cpp to 41ea26144e55d23f37bb765f88c07588d786567f (#8317) LocalAI [bot] 2026-01-31 22:18:31 +01:00
  • b05e110aa6 chore: ⬆️ Update ggml-org/llama.cpp to 1488339138d609139c4400d1b80f8a5b1a9a203c (#8306) LocalAI [bot] 2026-01-31 08:59:09 +01:00
  • e69cba2444 chore: ⬆️ Update ggml-org/whisper.cpp to aa1bc0d1a6dfd70dbb9f60c11df12441e03a9075 (#8305) LocalAI [bot] 2026-01-31 08:58:54 +01:00
  • f7903597ac chore(model-gallery): ⬆️ update checksum (#8307) LocalAI [bot] 2026-01-30 21:27:48 +01:00
  • ee76a0cd1c feat(swagger): update swagger (#8304) LocalAI [bot] 2026-01-30 21:27:10 +01:00
  • 4ca5b737bf chore(cuda): target 12.8 for 12 to increase compatibility (#8297) Ettore Di Giacinto 2026-01-30 12:58:44 +01:00
  • 4077aaf978 chore: re-enable e2e tests, fixups anthropic API tools support (#8296) Ettore Di Giacinto 2026-01-30 12:41:50 +01:00
  • 68dd9765a0 feat(tts): add support for streaming mode (#8291) Ettore Di Giacinto 2026-01-30 11:58:01 +01:00
  • 2c44b06a67 chore: ⬆️ Update ggml-org/llama.cpp to 4fdbc1e4dba428ce0cf9d2ac22232dc170bbca82 (#8283) LocalAI [bot] 2026-01-29 23:43:29 +01:00
  • 7cc90db3e5 chore(model-gallery): ⬆️ update checksum (#8285) LocalAI [bot] 2026-01-29 21:51:18 +01:00
  • 1e08e02598 feat(qwen-asr): add support to qwen-asr (#8281) Ettore Di Giacinto 2026-01-29 21:50:35 +01:00
  • dd8e74a486 feat(realtime): Add audio conversations (#6245) Richard Palethorpe 2026-01-29 07:44:53 +00:00
  • 48e08772f3 chore(llama.cpp): bump to 'f6b533d898ce84bae8d9fa8dfc6697ac087800bf' (#8275) Ettore Di Giacinto 2026-01-29 00:22:25 +01:00
  • c28c0227c6 chore: ⬆️ Update leejet/stable-diffusion.cpp to e411520407663e1ddf8ff2e5ed4ff3a116fbbc97 (#8274) LocalAI [bot] 2026-01-28 22:23:05 +01:00
  • 856ca2d6b1 fix(qwen3): Be explicit with function calling format (#8265) Richard Palethorpe 2026-01-28 13:44:29 +00:00
  • 9b973b79f6 feat: add VoxCPM tts backend (#8109) Ettore Di Giacinto 2026-01-28 14:44:04 +01:00
  • cba8ef4e38 chore: fix backend icons Ettore Di Giacinto 2026-01-28 09:09:00 +01:00
  • f729e300d6 chore: fix backend icons Ettore Di Giacinto 2026-01-28 09:08:03 +01:00
  • 9916811a79 chore: ⬆️ Update ggml-org/llama.cpp to 2b4cbd2834e427024bc7f935a1f232aecac6679b (#8258) LocalAI [bot] 2026-01-28 08:50:16 +01:00
  • 2f7c595cd1 chore(model gallery): add z-image and z-image-turbo for diffusers (#8260) Ettore Di Giacinto 2026-01-27 22:42:10 +01:00
  • 73decac746 chore(model gallery): Add mistral-community/pixtral-12b with mmproj (#8245) rampa3 2026-01-27 21:43:31 +01:00
  • ec1598868b feat(vibevoice): add ASR support (#8222) Ettore Di Giacinto 2026-01-27 20:19:22 +01:00
  • 93d7e5d4b8 chore(model gallery): Add entry for Magistral Small 1.2 with mmproj (#8248) rampa3 2026-01-27 16:55:00 +01:00
  • ff5a54b9d1 chore(model gallery): Add entry for Mistral Small 3.1 with mmproj (#8247) rampa3 2026-01-27 16:54:14 +01:00
  • 3c1f823c47 chore: ⬆️ Update ggml-org/llama.cpp to 8f80d1b254aef70a0959e314be368d05debe7294 (#8229) LocalAI [bot] 2026-01-26 22:19:43 +01:00
  • 4024220d00 chore(model gallery): 🤖 add 1 new models via gallery agent (#8220) LocalAI [bot] 2026-01-26 12:11:24 +01:00
  • f76958d761 chore: ⬆️ Update ggml-org/llama.cpp to 0440bfd1605333726ea0fb7a836942660bf2f9a6 (#8216) LocalAI [bot] 2026-01-26 00:50:35 +01:00
  • 2bd5ca45de chore: ⬆️ Update leejet/stable-diffusion.cpp to 43e829f21966abb96b08c712bccee872dc820914 (#8215) LocalAI [bot] 2026-01-26 00:50:16 +01:00
  • 6804ce1c39 chore(docs): change MEMORY_FILE_PATH to MEMORY_INDEX_PATH Ettore Di Giacinto 2026-01-25 22:14:11 +01:00
  • d499071bff fix(ui): correctly display selected image model (#8208) Dedy F. Setyawan 2026-01-25 20:54:40 +07:00
  • 26a374b717 chore: drop bark which is unmaintained (#8207) Ettore Di Giacinto 2026-01-25 09:26:40 +01:00
  • 980de0e25b chore(model gallery): Add most of not yet present Piper voices from Hugging Face (#8202) rampa3 2026-01-25 08:56:53 +01:00
  • 4767371aee chore(README): Add links Ettore Di Giacinto 2026-01-24 22:49:27 +01:00
  • 131d247b78 chore(README): Update and simplify links Ettore Di Giacinto 2026-01-24 22:46:40 +01:00
  • b2a8a63899 feat(vllm-omni): add new backend (#8188) Ettore Di Giacinto 2026-01-24 22:23:30 +01:00
  • 05a332cd5f chore: ⬆️ Update ggml-org/llama.cpp to bb02f74c612064947e51d23269a1cf810b67c9a7 (#8196) LocalAI [bot] 2026-01-24 22:19:43 +01:00
  • 05904c77f5 chore(exllama): drop backend now almost deprecated (#8186) Ettore Di Giacinto 2026-01-24 08:57:37 +01:00
  • 17783fa7d9 chore: ⬆️ Update leejet/stable-diffusion.cpp to fa61ea744d1a87fa26a63f8a86e45587bc9534d6 (#8184) LocalAI [bot] 2026-01-24 08:57:24 +01:00
  • 4019094111 chore: ⬆️ Update ggml-org/llama.cpp to 557515be1e93ed8939dd8a7c7d08765fdbe8be31 (#8183) LocalAI [bot] 2026-01-24 08:57:08 +01:00
  • ca65fc751a chore(model gallery): add qwen3-tts to model gallery (#8187) Ettore Di Giacinto 2026-01-23 23:06:50 +01:00
  • a1e3acc590 docs: ⬆️ update docs version mudler/LocalAI (#8182) LocalAI [bot] 2026-01-23 22:03:47 +01:00
  • a36960e069 fix(qwen-tts): change icon URL in index.yaml Ettore Di Giacinto 2026-01-23 22:00:14 +01:00
  • 58bb6a29ed Revert "chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/bark in the pip group across 1 directory" (#8180) Ettore Di Giacinto 2026-01-23 17:25:04 +01:00
  • 5881c82413 chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/bark in the pip group across 1 directory (#8175) dependabot[bot] 2026-01-23 15:32:15 +00:00
  • 923ebbb344 feat(qwen-tts): add Qwen-tts backend (#8163) v3.10.1 Ettore Di Giacinto 2026-01-23 15:18:41 +01:00
  • ea51567b89 chore(model gallery): 🤖 add 1 new models via gallery agent (#8170) LocalAI [bot] 2026-01-23 08:19:39 +01:00
  • 552c62a19c chore: ⬆️ Update leejet/stable-diffusion.cpp to 5e4579c11d0678f9765463582d024e58270faa9c (#8166) LocalAI [bot] 2026-01-23 08:18:05 +01:00
  • c0b21a921b feat: detect thinking support from backend automatically if not explicitly set (#8167) Ettore Di Giacinto 2026-01-23 00:38:28 +01:00
  • b10045adc2 chore: ⬆️ Update ggml-org/llama.cpp to a5eaa1d6a3732bc0f460b02b61c95680bba5a012 (#8165) LocalAI [bot] 2026-01-23 00:32:05 +01:00
  • 61b5e3b629 chore: drop test file Ettore Di Giacinto 2026-01-22 22:19:38 +00:00
  • e35d7cb3b3 chore: drop test file Ettore Di Giacinto 2026-01-22 21:47:50 +00:00
  • 0fa0ac4797 fix(videogen): drop incomplete endpoint, add GGUF support for LTX-2 (#8160) Ettore Di Giacinto 2026-01-22 14:09:20 +01:00
  • be7ed85838 chore(model gallery): 🤖 add 1 new models via gallery agent (#8157) LocalAI [bot] 2026-01-22 08:25:40 +01:00
  • c12b310028 chore: ⬆️ Update ggml-org/llama.cpp to c301172f660a1fe0b42023da990bf7385d69adb4 (#8151) LocalAI [bot] 2026-01-22 00:51:22 +01:00
  • 0447d5564d chore: ⬆️ Update leejet/stable-diffusion.cpp to 329571131d62d64a4f49e1acbef49ae02544fdcd (#8152) LocalAI [bot] 2026-01-22 00:50:41 +01:00
  • 22c0eb5421 chore(diffusers): add 'av' to requirements.txt (#8155) Ettore Di Giacinto 2026-01-21 22:35:00 +01:00
  • a0a00fb937 chore(model-gallery): ⬆️ update checksum (#8153) LocalAI [bot] 2026-01-21 21:45:11 +01:00
  • 6dd44742ea feat(swagger): update swagger (#8150) LocalAI [bot] 2026-01-21 21:44:44 +01:00
  • 00c72e7d3e fix(tracing): Create trace buffer on first request to enable tracing at runtime (#8148) Richard Palethorpe 2026-01-21 17:39:39 +00:00
  • d01c335cf6 chore: ⬆️ Update ggml-org/whisper.cpp to 7aa8818647303b567c3a21fe4220b2681988e220 (#8146) LocalAI [bot] 2026-01-21 17:44:01 +01:00
  • 5687df4535 chore: ⬆️ Update ggml-org/llama.cpp to ad8d85bd94cc86e89d23407bdebf98f2e6510c61 (#8145) LocalAI [bot] 2026-01-21 16:41:36 +01:00
  • f5fade97e6 chore: drop noisy logs (#8142) Ettore Di Giacinto 2026-01-21 09:52:20 +01:00
  • b88ae31e4e chore(model gallery): add flux 2 and flux 2 klein (#8141) Ettore Di Giacinto 2026-01-21 09:46:33 +01:00
  • f6daaa7c35 chore(deps): Bump llama.cpp to '1c7cf94b22a9dc6b1d32422f72a627787a4783a3' (#8136) Ettore Di Giacinto 2026-01-21 00:12:13 +01:00