Commit Graph

  • edeacf22c4 fix(realtime): keep transcription model on a language-only session.update (#10295) LocalAI [bot] 2026-06-13 01:01:36 +02:00
  • 3c74e53d87 fix(qwen-tts): install flash-attn on cuda13 images (#9293) fix/9293-qwen-tts-cuda13-flashattn Ettore Di Giacinto 2026-06-12 22:24:03 +00:00
  • 69c7a8e71d fix(mlx): strip file:// LocalPrefix before loading filesystem-imported models fix/7461-mlx-file-uri Ettore Di Giacinto 2026-06-12 22:07:06 +00:00
  • 69e482b0a8 fix(model): deterministic, file-type-filtered backend auto-detect (#9287) fix/9287-backend-autodetect Ettore Di Giacinto 2026-06-12 21:46:25 +00:00
  • 390664ff72 fix(responses): classify streamed reasoning as a reasoning item live (#9658) fix/9658-responses-streaming-reasoning Ettore Di Giacinto 2026-06-12 21:39:42 +00:00
  • 51f4f67c47 fix(agents): emit chat event timestamps in milliseconds (#9867) (#10243) Aniruddh Jha 2026-06-12 23:18:44 +02:00
  • cf71e291b4 fix(darwin): fix vibevoice-cpp build linkage + fail-safe go backend packaging (#10276) LocalAI [bot] 2026-06-12 23:13:50 +02:00
  • a7a7bd646b fix(mlx): route vision-language models to the mlx-vlm backend (#10274) LocalAI [bot] 2026-06-12 23:12:42 +02:00
  • cec93d2e00 docs: ⬆️ update docs version mudler/LocalAI (#10279) LocalAI [bot] 2026-06-12 23:12:30 +02:00
  • 722bdb87e9 chore: ⬆️ Update mudler/parakeet.cpp to b8012f11e5269126eddb7f4fd02f891a2ccc29b0 (#10281) LocalAI [bot] 2026-06-12 23:12:04 +02:00
  • 50dea8c983 feat(crispasr): bundle espeak-ng and add piper TTS voices to the gallery (#10283) LocalAI [bot] 2026-06-12 23:10:30 +02:00
  • 46ba70632b fix(crispasr): write piper TTS WAV at the model's native sample rate (#10277) LocalAI [bot] 2026-06-12 23:10:17 +02:00
  • 60facc7252 fix(darwin): publish sherpa-onnx and speaker-recognition images for darwin/arm64 (#10275) LocalAI [bot] 2026-06-12 22:32:42 +02:00
  • 8c8204d3c4 feat(parakeet-cpp): enable GGML_CUDA_GRAPHS in the cublas build (#10273) LocalAI [bot] 2026-06-12 18:47:36 +02:00
  • 4ce0f6102a chore(model gallery): 🤖 add 1 new models via gallery agent (#10270) LocalAI [bot] 2026-06-12 16:21:35 +02:00
  • 085fc53bbc fix(router): production-ready request router + auto-size batch for embedding/rerank (#10104) Richard Palethorpe 2026-06-12 15:21:15 +01:00
  • 56cc4f63fc feat(backend): locate-anything-cpp (open-vocabulary object detection via ggml) (#10264) LocalAI [bot] 2026-06-12 14:59:07 +02:00
  • a53f34e78f chore: ⬆️ Update ggml-org/llama.cpp to 4c6595503fe45d5a39f88d194e270f64c7424677 (#10261) LocalAI [bot] 2026-06-12 14:57:52 +02:00
  • 1cea96f09f feat(react-ui): add Indonesian language support (#10266) Dedy F. Setyawan 2026-06-12 15:08:58 +07:00
  • 006a9d38c7 chore: ⬆️ Update mudler/parakeet.cpp to 9db92be63179a27201d3b88d5d40c545b2ac48ae (#10263) LocalAI [bot] 2026-06-12 09:18:21 +02:00
  • 892ce951ce chore: ⬆️ Update antirez/ds4 to d881f2a05e8ff6bec001315a36b794b4aa310173 (#10262) LocalAI [bot] 2026-06-12 09:18:07 +02:00
  • 7cda221d36 docs: ⬆️ update docs version mudler/LocalAI (#10259) LocalAI [bot] 2026-06-12 09:17:49 +02:00
  • 9a88eb81e7 chore: ⬆️ Update CrispStrobe/CrispASR to d745bda4386ae0f9d1d2f23fff8ec95d76428221 (#10260) LocalAI [bot] 2026-06-12 09:17:34 +02:00
  • b40843cf62 feat(dllm): image input through the backend (multimodal C-ABI) Ettore Di Giacinto 2026-06-12 00:41:04 +00:00
  • 58cdc050e9 fix(cuda): install cuda-nvrtc-dev alongside the other CUDA dev packages (#10257) v4.4.2 pos-ei-don 2026-06-11 23:57:00 +02:00
  • b962f4a192 fix(vllm): parse tool_call function arguments before applying the chat template (#10256) pos-ei-don 2026-06-11 23:55:38 +02:00
  • c9c6040fe8 feat(dllm): default gallery entry on Q4_K_M; add Q8_0 variant Ettore Di Giacinto 2026-06-11 20:24:26 +00:00
  • 8134d6db37 docs(dllm): record Q4_K_M validation and quantization guidance Ettore Di Giacinto 2026-06-11 19:22:02 +00:00
  • ad6d1dbc8b feat(grpc): request cancellation for Go backends via the Cancellable capability Ettore Di Giacinto 2026-06-11 17:50:04 +00:00
  • eb61e1d770 chore(dllm): review fixes - file modes and build-matrix doc accuracy Ettore Di Giacinto 2026-06-11 17:17:54 +00:00
  • aba9c4794a docs(dllm): backend documentation and agents topic guide Ettore Di Giacinto 2026-06-11 17:05:18 +00:00
  • 04d6f66a9a feat(dllm): diffusiongemma gallery entry and e2e coverage Ettore Di Giacinto 2026-06-11 17:05:18 +00:00
  • 52b3b68cea feat(dllm): backend packaging, gallery index, CI matrix Ettore Di Giacinto 2026-06-11 17:05:18 +00:00
  • b6fcb3e1db chore: ⬆️ Update CrispStrobe/CrispASR to 4b27392ffd0991a857594652cbb8b57e585bcd7b (#10241) LocalAI [bot] 2026-06-11 18:33:58 +02:00
  • ff09683d84 chore: ⬆️ Update ggml-org/llama.cpp to ac4cddeb0dbd778f650bf568f6f08344a06abe3a (#10239) LocalAI [bot] 2026-06-11 18:33:38 +02:00
  • f618636c71 docs: fix broken relref to realtime page (#10255) v4.4.1 LocalAI [bot] 2026-06-11 18:32:50 +02:00
  • 99184809fa feat(dllm): rich gRPC backend with ChatDelta streaming Ettore Di Giacinto 2026-06-11 16:14:37 +00:00
  • 294c04ae2f feat(dllm): gemma4 streaming parser emitting ChatDeltas Ettore Di Giacinto 2026-06-11 15:55:27 +00:00
  • 778f85c2a0 feat(dllm): purego backend scaffold over the dllm.cpp C-ABI Ettore Di Giacinto 2026-06-11 14:50:39 +00:00
  • af0db1419c test(http): make the suite listen port configurable Ettore Di Giacinto 2026-06-11 14:28:39 +00:00
  • 892fc49949 feat(realtime): stream the LLM / TTS / transcription pipeline stages (#10176) LocalAI [bot] 2026-06-11 09:43:12 +02:00
  • 228a6dfe79 fix(vllm): restore compatibility with vLLM >= 0.22 (get_tokenizer moved to vllm.tokenizers) (#10252) pos-ei-don 2026-06-11 09:05:23 +02:00
  • 51a92b6093 chore: ⬆️ Update antirez/ds4 to 8384adf0f9fa0f3bb342dd925372de778b95b263 (#10242) LocalAI [bot] 2026-06-11 00:10:34 +02:00
  • b5964d385d docs: ⬆️ update docs version mudler/LocalAI (#10245) LocalAI [bot] 2026-06-11 00:10:10 +02:00
  • fba8c9c498 fix(distributed): track in-flight for non-LLM inference methods (VAD, diarize, voice, ...) (#10238) v4.4.0 LocalAI [bot] 2026-06-10 16:29:50 +02:00
  • 6b2badb837 chore: ⬆️ Update CrispStrobe/CrispASR to c29f6653a516a3001d923944dad8892072cc7334 (#10236) LocalAI [bot] 2026-06-10 16:16:24 +02:00
  • 8b8506d01a chore: ⬆️ Update ggml-org/llama.cpp to 039e20a2db9e87b2477c76cc04905f3e1acad77f (#10223) LocalAI [bot] 2026-06-10 12:22:03 +02:00
  • 6910a0bb48 chore: ⬆️ Update antirez/ds4 to 91bafb5acd5a6cf00b1e55ef68bf40ddd207bee7 (#10234) LocalAI [bot] 2026-06-10 12:08:19 +02:00
  • cffd03b522 chore: ⬆️ Update ikawrakow/ik_llama.cpp to e6f8112f3ba126eed3ff5b30cdd08085414a7516 (#10233) LocalAI [bot] 2026-06-10 12:07:49 +02:00
  • bf448d3794 chore: ⬆️ Update ggml-org/whisper.cpp to df7638d8229a243af8a4b5a8ae557e0d74e0a0ae (#10220) LocalAI [bot] 2026-06-10 01:16:29 +02:00
  • 1d4a12f7c0 chore: ⬆️ Update CrispStrobe/CrispASR to 97cad527d247edefc904e6c40c4cf5ee78bed055 (#10221) LocalAI [bot] 2026-06-10 01:16:17 +02:00
  • 186d62801d chore: ⬆️ Update leejet/stable-diffusion.cpp to 19bdfe22d255d5b4dff39d449318b9bc5ea2317f (#10222) LocalAI [bot] 2026-06-10 01:16:06 +02:00
  • da4ed05429 chore: ⬆️ Update ikawrakow/ik_llama.cpp to 2768b6251548b78b6610e95edad13f888ad95982 (#10219) LocalAI [bot] 2026-06-10 01:15:54 +02:00
  • ec1eea4f45 chore: ⬆️ Update antirez/ds4 to 512d07cb08f234b704b5a5959aa9e2d4c466eeb0 (#10224) LocalAI [bot] 2026-06-10 01:15:42 +02:00
  • b203b32e57 feat(realtime): make WebRTC ICE candidates configurable (#10231) LocalAI [bot] 2026-06-09 22:28:03 +02:00
  • 48a8ce98aa fix(cli): handle chat output errors (#10229) Ching 2026-06-09 10:10:24 -07:00
  • 8344d1c865 feat(cli): add interactive chat mode (#10226) Ching 2026-06-09 07:58:44 -07:00
  • d2e6b93369 feat(agents): surface KB source citations in RAG responses (#10228) Pete 2026-06-09 07:32:56 -07:00
  • e1ec03d33f fix(reasoning): stop prefilled <think> from swallowing tag-less answers (#10225) LocalAI [bot] 2026-06-09 09:02:04 +02:00
  • 9323f4b5ca feat(llama-cpp): video input support (mtmd #24269) (#10216) LocalAI [bot] 2026-06-08 23:17:50 +02:00
  • e90d2f42f2 chore(deps): update transformers requirement dependabot/pip/backend/python/transformers/transformers-gte-5.10.2 dependabot[bot] 2026-06-08 18:33:54 +00:00
  • fbb1d05389 chore(deps): bump transformers in /backend/python/coqui dependabot/pip/backend/python/coqui/transformers-5.10.2 dependabot[bot] 2026-06-08 18:33:33 +00:00
  • c20225fc13 chore: ⬆️ Update CrispStrobe/CrispASR to f7838a306687f22c281d29c250f879a4ab3df2d7 (#10177) LocalAI [bot] 2026-06-08 16:01:19 +02:00
  • 337acc4c37 chore: ⬆️ Update antirez/ds4 to c463029c205c2ec8d7ab6c0df4a3f52979091286 (#10189) LocalAI [bot] 2026-06-08 11:15:32 +02:00
  • 618e90cd13 feat(gallery): add Gemma 4 QAT family + MTP speculative-decoding pairs (#10215) LocalAI [bot] 2026-06-08 10:26:42 +02:00
  • 92dea961c2 fix: distributed backend reinstall/upgrade UI stuck on 'reinstalling' (#10214) LocalAI [bot] 2026-06-08 10:03:02 +02:00
  • 2e93186043 chore: ⬆️ Update ggml-org/llama.cpp to 9e3b928fd8c9d14dbf15a8768b9fdd7e5c721d66 (#10210) LocalAI [bot] 2026-06-08 09:35:17 +02:00
  • d07037e817 chore: ⬆️ Update leejet/stable-diffusion.cpp to b3d56d0ba1bd437886079e339118e8e75bb79ee7 (#10211) LocalAI [bot] 2026-06-08 09:03:57 +02:00
  • f6cc90d258 chore: ⬆️ Update mudler/parakeet.cpp to e270af73b94c9a5c37ec516230219ed4580e1db6 (#10212) LocalAI [bot] 2026-06-07 23:52:44 +02:00
  • 2c804bef5a fix(config): skip vocab arrays and mmap GGUF headers to speed up startup (#10213) Adira 2026-06-08 00:33:52 +03:00
  • 6070402477 chore(model gallery): 🤖 add 1 new models via gallery agent (#10209) LocalAI [bot] 2026-06-07 22:09:32 +02:00
  • 67f80a152b fix(mtp): don't auto-enable self-spec MTP for draft-only assistant GGUFs (#10208) LocalAI [bot] 2026-06-07 22:09:02 +02:00
  • a7cb587d96 feat(parakeet-cpp): real segment timestamps (NeMo-faithful) (#10207) LocalAI [bot] 2026-06-07 22:08:24 +02:00
  • f7c74ad2da chore: ⬆️ Update ggml-org/llama.cpp to 31e82494c0a3913c919c1027fa70500fbf4c07dd (#10191) LocalAI [bot] 2026-06-07 10:43:17 +02:00
  • 7402d1fd20 chore(turboquant): bump to 7d9715f1 + fix compilation against rebased fork (#10205) LocalAI [bot] 2026-06-07 10:42:06 +02:00
  • 8c42695ef8 chore: ⬆️ Update ggml-org/whisper.cpp to a8ec021f2750a473ff4a8f3883bc9fdf5feafa84 (#10202) LocalAI [bot] 2026-06-07 08:37:42 +02:00
  • 72e3241431 chore: ⬆️ Update mudler/parakeet.cpp to abd0087dcc92ec5ad1f96f9fd86c49eb26a5ce67 (#10204) LocalAI [bot] 2026-06-07 00:37:28 +02:00
  • cd2bf95862 fix(docs): use relearn notice shortcode instead of unsupported alert (#10206) LocalAI [bot] 2026-06-07 00:37:12 +02:00
  • f64b72dd7d feat: support Ideogram4 in stablediffusion-ggml backend + gallery (#10201) LocalAI [bot] 2026-06-06 22:50:12 +02:00
  • 03c84cff28 feat(parakeet-cpp): nemotron-3.5-asr multilingual streaming model + request language support (#10199) LocalAI [bot] 2026-06-06 13:53:10 +02:00
  • 9bc69c9e5f chore(model gallery): 🤖 add 1 new models via gallery agent (#10200) LocalAI [bot] 2026-06-06 13:52:46 +02:00
  • 1e6c9cfd60 chore: ⬆️ Update ikawrakow/ik_llama.cpp to 6b9de3dbaa21ae95ea80638e5ee836795cc48c93 (#10190) LocalAI [bot] 2026-06-06 09:42:43 +02:00
  • 0e6712f734 chore: ⬆️ Update mudler/parakeet.cpp to 843600590f96a31467a5199f827c253f34c110f7 (#10198) LocalAI [bot] 2026-06-06 09:25:25 +02:00
  • 0e4cee9a97 chore: bump LocalAGI + localrecall (fix pgvector hybrid search seqscan, #10186) (#10192) LocalAI [bot] 2026-06-06 09:16:59 +02:00
  • b15627c864 chore(deps): bump the pip group across 1 directory with 2 updates dependabot/pip/backend/python/coqui/pip-842ffb7a79 dependabot[bot] 2026-06-05 23:31:21 +00:00
  • 2342c9348e chore(deps): bump torch dependabot/pip/backend/python/transformers/pip-f98efa472c dependabot[bot] 2026-06-05 23:31:07 +00:00
  • cb4a612bab chore(deps): bump torch dependabot/pip/backend/python/rerankers/pip-f98efa472c dependabot[bot] 2026-06-05 23:31:06 +00:00
  • 352b7ec604 Harden gallery-agent Hugging Face fetches against transient rate limiting (#10187) Copilot 2026-06-05 23:43:06 +02:00
  • ba706422fb chore: ⬆️ Update vllm-project/vllm cu130 wheel to 0.22.1 (#10188) LocalAI [bot] 2026-06-05 23:42:50 +02:00
  • e837921c2c feat: forward reasoning_effort to the backend so jinja models honor it (#10184) LocalAI [bot] 2026-06-05 15:45:43 +02:00
  • 73385713ca feat(distributed): enforce registration token for worker file transfer (#10183) Richard Palethorpe 2026-06-05 13:34:28 +01:00
  • a4e671779a chore: ⬆️ Update ggml-org/whisper.cpp to 99613cb720b65036237d44b52f753b51f75c2797 (#10178) LocalAI [bot] 2026-06-05 09:04:25 +02:00
  • 7051b2e0a1 chore: ⬆️ Update ggml-org/llama.cpp to 7c158fbb4aec1bdc9c81d6ca0e785139f4826fae (#10179) LocalAI [bot] 2026-06-05 09:04:10 +02:00
  • 469737101a chore: ⬆️ Update ikawrakow/ik_llama.cpp to 1520eda980564241434b791ce2bbbd128c4be9ea (#10180) LocalAI [bot] 2026-06-05 09:03:08 +02:00
  • 858257eaf0 fix(distributed): self-heal stale 'model not loaded' routing (#10181) LocalAI [bot] 2026-06-05 09:01:36 +02:00
  • ef80a0e825 fix(config): add face/speaker recognition constants and register insightface + speaker-recognition (#10110) Adira 2026-06-04 22:48:01 +03:00
  • 92726f7631 fix(distributed): stage directory-based models to remote nodes (#10175) LocalAI [bot] 2026-06-04 18:05:38 +02:00
  • 994063ba9a feat(qwen3-tts-cpp): normalize request language for flexible matching (#10174) LocalAI [bot] 2026-06-04 17:26:31 +02:00
  • c1a55cf72d chore: ⬆️ Update mudler/parakeet.cpp to b11fe5bca78ad8b342dd559a43d76df3984bb447 (#10167) LocalAI [bot] 2026-06-04 12:07:09 +02:00
  • 96758841d8 chore: ⬆️ Update predict-woo/qwen3-tts.cpp to 136e5d36c17083da0321fd96512dc7b263f94a44 (#10165) LocalAI [bot] 2026-06-04 12:06:55 +02:00