Commit Graph

  • 0f9d516a6c fix(anthropic): do not emit empty tokens and fix SSE tool calls (#9258) Ettore Di Giacinto 2026-04-07 00:38:21 +02:00
  • 33b124c6f1 chore(deps): bump github.com/aws/aws-sdk-go-v2/config from 1.32.12 to 1.32.14 (#9256) dependabot[bot] 2026-04-06 21:46:52 +02:00
  • 6b8007e88e chore(deps): bump github.com/jaypipes/ghw from 0.23.0 to 0.24.0 (#9250) dependabot[bot] 2026-04-06 21:46:18 +02:00
  • b3837c2078 chore(deps): bump google.golang.org/grpc from 1.79.3 to 1.80.0 (#9253) dependabot[bot] 2026-04-06 21:45:50 +02:00
  • 92f99b1ec3 fix(token): login via legacy api keys (#9249) Ettore Di Giacinto 2026-04-06 21:45:09 +02:00
  • ad232fdb1a docs: ⬆️ update docs version mudler/LocalAI (#9241) v4.1.2 LocalAI [bot] 2026-04-06 10:53:07 +02:00
  • 11637b5a1b chore: ⬆️ Update leejet/stable-diffusion.cpp to 7397ddaa86f4e8837d5261724678cde0f36d4d89 (#9242) LocalAI [bot] 2026-04-06 10:52:51 +02:00
  • 0dda4fe6f0 chore: ⬆️ Update ggml-org/llama.cpp to 761797ffdf2ce3f118e82c663b1ad7d935fbd656 (#9243) LocalAI [bot] 2026-04-06 10:52:38 +02:00
  • 773489eeb1 fix(chat): do not retry if we had chatdeltas or tooldeltas from backend (#9244) Ettore Di Giacinto 2026-04-06 10:52:23 +02:00
  • 06fbe48b3f feat(llama.cpp): wire speculative decoding settings (#9238) Ettore Di Giacinto 2026-04-05 14:56:30 +02:00
  • 232e324a68 fix(autoparser): correctly pass by logprobs (#9239) Ettore Di Giacinto 2026-04-05 09:39:22 +02:00
  • 39c954764c Update index.yaml and add Qwen3.5 model files (#9237) ER-EPR 2026-04-05 15:21:21 +08:00
  • 9b7d5513fc chore(gallery): add mmproj file for gemma4 v4.1.1 Ettore Di Giacinto 2026-04-05 02:02:52 +02:00
  • 84cd8c0e7f chore: ⬆️ Update ggml-org/llama.cpp to b8635075ffe27b135c49afb9a8b5c434bd42c502 (#9231) LocalAI [bot] 2026-04-04 23:02:58 +02:00
  • d990f2790c chore(model-gallery): ⬆️ update checksum (#9233) LocalAI [bot] 2026-04-04 23:02:41 +02:00
  • 53deeb1107 fix(reasoning): suppress partial tag tokens during autoparser warm-up Ettore Di Giacinto 2026-04-04 20:45:50 +00:00
  • c5a840f6af fix(reasoning): warm-up Ettore Di Giacinto 2026-04-04 20:25:24 +00:00
  • 6d9d77d590 fix(reasoning): accumulate and strip reasoning tags from autoparser results (#9227) Ettore Di Giacinto 2026-04-04 18:15:32 +02:00
  • 6f304d1201 chore(refactor): use interface (#9226) Ettore Di Giacinto 2026-04-04 17:29:37 +02:00
  • 557d0f0f04 feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084) Richard Palethorpe 2026-04-04 14:14:35 +01:00
  • b7e3589875 fix(anthropic): show null index when not present, default to 0 (#9225) Ettore Di Giacinto 2026-04-04 15:13:17 +02:00
  • 716ddd697b feat(autoparser): prefer chat deltas from backends when emitted (#9224) Ettore Di Giacinto 2026-04-04 12:12:08 +02:00
  • 223deb908d fix(nats): improve error handling (#9222) Ettore Di Giacinto 2026-04-04 12:11:54 +02:00
  • 9f8821bba8 feat(gemma4): add thinking support (#9221) Ettore Di Giacinto 2026-04-04 12:11:38 +02:00
  • 84e51b68ef fix(ui): pass by staticApiKeyRequired to show login when only api key is configured (#9220) Ettore Di Giacinto 2026-04-04 12:11:22 +02:00
  • 7962dd16f7 chore: ⬆️ Update ggml-org/llama.cpp to d006858316d4650bb4da0c6923294ccd741caefd (#9215) LocalAI [bot] 2026-04-04 09:44:39 +02:00
  • a1466b305a docs: ⬆️ update docs version mudler/LocalAI (#9214) LocalAI [bot] 2026-04-04 09:44:25 +02:00
  • 57c0026715 chore: bump inference defaults from unsloth (#9219) github-actions[bot] 2026-04-04 09:44:12 +02:00
  • 1ed6b9e5ed fix(llama.cpp): correctly parse grpc header for bearer token auth Ettore Di Giacinto 2026-04-03 21:38:41 +00:00
  • 6e11f882f7 feat(turboquant.cpp): add new backend feat/tq-ik Ettore Di Giacinto 2026-04-03 20:53:30 +00:00
  • e4ee74354f chore(model gallery): 🤖 add 1 new models via gallery agent (#9210) LocalAI [bot] 2026-04-03 16:23:17 +02:00
  • 8577bdcebc Update asset links in README.md Ettore Di Giacinto 2026-04-03 10:24:08 +02:00
  • 0d489c7a0d Add guided tour and update screenshots section Ettore Di Giacinto 2026-04-03 10:23:03 +02:00
  • 11dc54bda9 fix(docs): commit distribution.md Ettore Di Giacinto 2026-04-03 10:14:13 +02:00
  • 7e0b73deaa fix(docs): fix broken references to distributed mode Ettore Di Giacinto 2026-04-03 09:46:06 +02:00
  • c0a023d13d chore: ⬆️ Update ggml-org/llama.cpp to a1cfb645307edc61a89e41557f290f441043d3c2 (#9203) LocalAI [bot] 2026-04-03 08:30:15 +02:00
  • 0d3ae1c295 docs: Update Home Assistant integrations list (#9206) Loryan Strant 2026-04-03 17:30:00 +11:00
  • e9f10f2f50 chore(model gallery): 🤖 add 1 new models via gallery agent (#9202) v4.1.0 LocalAI [bot] 2026-04-02 21:22:19 +02:00
  • b95b0b72ff chore(ci): fix gallery agent Ettore Di Giacinto 2026-04-02 17:17:15 +00:00
  • 26f1b94f4d chore: ⬆️ Update ggml-org/llama.cpp to 95a6ebabb277c4cc18247e7bc2a5502133caca63 (#9199) LocalAI [bot] 2026-04-02 08:53:16 +02:00
  • 2d40725ca2 chore: ⬆️ Update leejet/stable-diffusion.cpp to 87ecb95cbc65dc8e58e3d88f4f4a59a0939796f5 (#9200) LocalAI [bot] 2026-04-02 08:53:04 +02:00
  • 659636195c deterministic builds feat/turboquant Ettore Di Giacinto 2026-04-01 19:45:31 +00:00
  • a7a142b651 refactor, macOS fixes Ettore Di Giacinto 2026-04-01 19:42:16 +00:00
  • e502e51d78 feat(llama.cpp): add turboquant support Ettore Di Giacinto 2026-04-01 17:46:44 +00:00
  • 6c635e8353 feat: add resume endpoint to undrain nodes (#9197) Ettore Di Giacinto 2026-04-01 18:21:43 +02:00
  • cc5f33ce95 chore: ⬆️ Update ggml-org/llama.cpp to 0fcb3760b2b9a3a496ef14621a7e4dad7a8df90f (#9196) LocalAI [bot] 2026-04-01 00:48:40 +02:00
  • ba7cdd532a chore: ⬆️ Update leejet/stable-diffusion.cpp to 09b12d5f6d51d862749e8e0ee8baac8f012089e2 (#9195) LocalAI [bot] 2026-04-01 00:48:25 +02:00
  • 6b6c136210 fix(inflight): count inflight from load model, but release afterwards (#9194) Ettore Di Giacinto 2026-03-31 23:24:45 +02:00
  • e587ecc485 chore(ui): allow to unload forcefully Ettore Di Giacinto 2026-03-31 17:20:53 +00:00
  • f259036a27 feat(gpu): add jetson/tegra detection Ettore Di Giacinto 2026-03-31 15:45:00 +00:00
  • 221ff0f28f feat(ui): show cluster status in home in distributed mode Ettore Di Giacinto 2026-03-31 15:37:58 +00:00
  • 16d5cb00bd chore: css cleanups Ettore Di Giacinto 2026-03-31 16:37:38 +02:00
  • 952635fba6 feat(distributed): Avoid resending models to backend nodes (#9193) Richard Palethorpe 2026-03-31 15:28:13 +01:00
  • 3cc05af2e5 chore(nodes): restore offline nodes too Ettore Di Giacinto 2026-03-31 14:22:08 +00:00
  • 87a63316c7 stablediffusion-ggml: replace hand-maintained enum string arrays with upstream API calls (#9192) Copilot 2026-03-31 14:53:38 +02:00
  • efdcbbe332 feat(api): Return 404 when model is not found except for model names in HF format (#9133) Richard Palethorpe 2026-03-31 09:48:21 +01:00
  • b4fff9293d chore: small ui improvements in the node page Ettore Di Giacinto 2026-03-31 08:41:40 +00:00
  • 8180221b7e chore(deps): bump grpcio from 1.78.1 to 1.80.0 in /backend/python/common/template (#9176) dependabot[bot] 2026-03-31 10:11:04 +02:00
  • 52a9755e08 chore(deps): bump grpcio from 1.78.1 to 1.80.0 in /backend/python/rerankers (#9181) dependabot[bot] 2026-03-31 10:10:50 +02:00
  • a2a1d919f9 chore(deps): bump grpcio from 1.78.1 to 1.80.0 in /backend/python/coqui (#9182) dependabot[bot] 2026-03-31 10:10:35 +02:00
  • a3d37931ec chore(deps): bump grpcio from 1.78.1 to 1.80.0 in /backend/python/vllm (#9177) dependabot[bot] 2026-03-31 10:10:17 +02:00
  • 5b2e25ebb0 chore(deps): bump grpcio from 1.78.1 to 1.80.0 in /backend/python/transformers (#9180) dependabot[bot] 2026-03-31 10:10:03 +02:00
  • b0b37a472f chore: ⬆️ Update ggml-org/llama.cpp to 08f21453aec846867b39878500d725a05bd32683 (#9190) LocalAI [bot] 2026-03-31 09:27:08 +02:00
  • 3db12eaa7a fix(oauth/invite): do not register user (prending approval) without correct invite (#9189) Ettore Di Giacinto 2026-03-31 08:29:07 +02:00
  • 8862e3ce60 feat: add node reconciler, allow to schedule to group of nodes, min/max autoscaler (#9186) Ettore Di Giacinto 2026-03-31 08:28:56 +02:00
  • 80699a3f70 feat(swagger): update swagger (#9187) LocalAI [bot] 2026-03-30 23:48:06 +02:00
  • 309a59f61e chore(deps): bump actions/upload-pages-artifact from 3 to 4 (#9179) dependabot[bot] 2026-03-30 23:16:23 +02:00
  • 65c9380389 chore(deps): bump go.opentelemetry.io/otel/exporters/prometheus from 0.62.0 to 0.64.0 (#9178) dependabot[bot] 2026-03-30 23:16:09 +02:00
  • 79963c56bf chore(deps): bump github.com/pion/webrtc/v4 from 4.2.9 to 4.2.11 (#9185) dependabot[bot] 2026-03-30 23:15:54 +02:00
  • 7004ce0b78 chore(deps): bump github.com/nats-io/nats.go from 1.49.0 to 1.50.0 (#9183) dependabot[bot] 2026-03-30 23:15:39 +02:00
  • 702d0e0e4d chore(deps): bump google.golang.org/grpc from 1.79.1 to 1.79.3 (#9175) dependabot[bot] 2026-03-30 23:15:25 +02:00
  • d6de208d6c chore(deps): bump actions/configure-pages from 5 to 6 (#9174) dependabot[bot] 2026-03-30 23:15:10 +02:00
  • 7451145e0c chore(deps): bump actions/deploy-pages from 4 to 5 (#9172) dependabot[bot] 2026-03-30 23:14:57 +02:00
  • cfda3dd0df chore(deps): bump actions/checkout from 4 to 6 (#9173) dependabot[bot] 2026-03-30 23:14:43 +02:00
  • e0eb2fd734 chore(ci): Scope tests extras backend tests (#9170) Richard Palethorpe 2026-03-30 18:46:07 +01:00
  • dd3376e0a9 chore(workers): improve logging, set header timeouts (#9171) Ettore Di Giacinto 2026-03-30 17:26:55 +02:00
  • 520e1ce3cd fix(kokoro): Download phonemization model during installation (#9165) Richard Palethorpe 2026-03-30 14:08:48 +01:00
  • 3d738164b7 chore: ⬆️ Update ggml-org/llama.cpp to 7c203670f8d746382247ed369fea7fbf10df8ae0 (#9160) LocalAI [bot] 2026-03-30 08:27:26 +02:00
  • 56db76599a chore: ⬆️ Update ggml-org/whisper.cpp to 95ea8f9bfb03a15db08a8989966fd1ae3361e20d (#9168) LocalAI [bot] 2026-03-30 08:27:11 +02:00
  • ad57cdfefe chore: ⬆️ Update leejet/stable-diffusion.cpp to f16a110f8776398ef23a2a6b7b57522c2471637a (#9167) LocalAI [bot] 2026-03-30 08:26:45 +02:00
  • c2f7d1c18b feat(ui): Add media history to studio pages (e.g. past images) (#9151) Richard Palethorpe 2026-03-29 23:49:55 +01:00
  • afe79568d6 fix: huggingface repo change the file name so Update index.yaml is needed (#9163) ER-EPR 2026-03-30 06:48:17 +08:00
  • 59108fbe32 feat: add distributed mode (#9124) Ettore Di Giacinto 2026-03-30 00:47:27 +02:00
  • 4c870288d9 chore: ⬆️ Update ggml-org/llama.cpp to 59d840209a5195c2f6e2e81b5f8339a0637b59d9 (#9144) LocalAI [bot] 2026-03-28 18:18:06 +01:00
  • 8da7212763 fix(ci): checkout submodules Ettore Di Giacinto 2026-03-28 00:33:31 +01:00
  • 6e76052f9d ci: set gh-pages Ettore Di Giacinto 2026-03-27 21:26:55 +00:00
  • cf84db36ec fix(voxcpm): Force using a recent voxcpm version to kick the dependency solver (#9150) Richard Palethorpe 2026-03-27 14:38:51 +00:00
  • d3f629f183 feat: Merge repeated log lines in the terminal (#9141) Richard Palethorpe 2026-03-26 21:16:13 +00:00
  • b1aa707a92 fix(coqui,nemo,voxcpm): Add dependencies to allow CI to progress (#9142) Richard Palethorpe 2026-03-26 17:03:56 +00:00
  • 731176ce3a feat(swagger): update swagger (#9136) LocalAI [bot] 2026-03-26 07:58:11 +01:00
  • b86fa63f70 chore: ⬆️ Update ggml-org/llama.cpp to a970515bdb0b1d09519106847660b0d0c84d2472 (#9137) LocalAI [bot] 2026-03-26 07:56:41 +01:00
  • 00fcf6936c fix: implement encoding_format=base64 for embeddings endpoint (#9135) walcz-de 2026-03-25 17:38:07 +01:00
  • 26384c5c70 fix(docs): Use notice instead of alert (#9134) Richard Palethorpe 2026-03-25 12:55:48 +00:00
  • 7209457f53 chore: ⬆️ Update ace-step/acestep.cpp to 6f35c874ee11e86d511b860019b84976f5b52d3a (#9128) LocalAI [bot] 2026-03-25 07:52:31 +01:00
  • 9bc68b2721 chore: ⬆️ Update ggml-org/llama.cpp to 9f102a1407ed5d73b8c954f32edab50f8dfa3f58 (#9127) LocalAI [bot] 2026-03-25 07:52:14 +01:00
  • 7bdd198fd3 fix(downloader): Rewrite full https HF URI with HF_ENDPOINT (#9107) Richard Palethorpe 2026-03-24 17:32:52 +00:00
  • b296e3d94b chore(deps): bump github.com/mudler/skillserver from 0.0.5 to 0.0.6 (#9116) dependabot[bot] 2026-03-24 08:51:02 +01:00
  • c91855a9b2 chore(deps): bump peter-evans/create-pull-request from 7 to 8 (#9114) dependabot[bot] 2026-03-24 08:50:50 +01:00
  • e8e445cd43 chore(deps): bump actions/checkout from 4 to 6 (#9110) dependabot[bot] 2026-03-24 08:50:36 +01:00
  • 735c426072 chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.4.0 to 1.4.1 (#9118) dependabot[bot] 2026-03-24 00:36:23 +01:00