Commit Graph

  • fcecc12e57 chore: ⬆️ Update ggml-org/llama.cpp to ba3b9c8844aca35ecb40d31886686326f22d2214 (#8613) v3.12.1 LocalAI [bot] 2026-02-21 09:57:04 +01:00
  • 51902df7ba fix: merge openresponses messages (#8615) Ettore Di Giacinto 2026-02-21 09:56:43 +01:00
  • 05f3ae31de chore: drop bark.cpp leftovers from pipelines (#8614) Ettore Di Giacinto 2026-02-21 09:24:09 +01:00
  • bb0924dff1 chore: ⬆️ Update ggml-org/llama.cpp to b908baf1825b1a89afef87b09e22c32af2ca6548 (#8612) LocalAI [bot] 2026-02-20 23:47:47 +01:00
  • 51eec4e6b8 feat(traces): Add backend traces (#8609) Richard Palethorpe 2026-02-20 22:47:33 +00:00
  • 462c82fad2 docs: ⬆️ update docs version mudler/LocalAI (#8611) LocalAI [bot] 2026-02-20 22:19:51 +01:00
  • 352b8aaa1b fix(ui): pass by needed values to unbreak model editor v3.12.0 Ettore Di Giacinto 2026-02-20 09:06:17 +01:00
  • df792d6243 chore(ui): improve navigation and buttons placement (#8608) Ettore Di Giacinto 2026-02-19 23:41:05 +01:00
  • b1c434f0fc chore: ⬆️ Update ggml-org/llama.cpp to 11c325c6e0666a30590cde390d5746a405e536b9 (#8607) LocalAI [bot] 2026-02-19 23:32:35 +01:00
  • bb42b342de chore: ⬆️ Update ggml-org/whisper.cpp to 21411d81ea736ed5d9cdea4df360d3c4b60a4adb (#8606) LocalAI [bot] 2026-02-19 23:32:21 +01:00
  • e555057f8b fix: multi-GPU support for Diffusers (Issue #8575) (#8605) LocalAI [bot] 2026-02-19 21:35:58 +01:00
  • 76fba02e56 fix: do not keep track model if not existing (#8603) Ettore Di Giacinto 2026-02-19 17:18:38 +01:00
  • dadc7158fb fix(diffusers): sd_embed is not always available (#8602) Ettore Di Giacinto 2026-02-19 10:45:17 +01:00
  • 68c7077491 chore: ⬆️ Update ggml-org/llama.cpp to b55dcdef5dcd74dc75c4921090e928d43453c157 (#8599) LocalAI [bot] 2026-02-18 22:33:25 +01:00
  • b471619ad9 chore(deps): bump cogito and add new options to the agent config (#8601) Ettore Di Giacinto 2026-02-18 22:10:26 +01:00
  • a0476d5567 chore(model-gallery): ⬆️ update checksum (#8600) LocalAI [bot] 2026-02-18 21:52:28 +01:00
  • a2228f1418 fix(ui): improve view on mobile (#8598) Ettore Di Giacinto 2026-02-18 19:50:59 +01:00
  • 7dd9a155a3 fix(ui): drop duplicated footer import Ettore Di Giacinto 2026-02-18 14:38:53 +01:00
  • 4fe830ff58 fix(realtime): Limit buffer sizes to prevent DoS (#8596) Richard Palethorpe 2026-02-18 13:36:43 +00:00
  • 86b3bc9313 fix(realtime): Better support for thinking models and setting model parameters (#8595) Richard Palethorpe 2026-02-18 13:36:16 +00:00
  • 2fabdc08e6 feat(ui): left navbar, dark/light theme (#8594) Ettore Di Giacinto 2026-02-18 00:14:39 +01:00
  • ed832cf0e0 chore: ⬆️ Update ggml-org/llama.cpp to 2b089c77580d347767f440205103e4da8ec33d89 (#8592) LocalAI [bot] 2026-02-17 23:35:07 +01:00
  • 95db1da309 chore(model-gallery): ⬆️ update checksum (#8593) LocalAI [bot] 2026-02-17 21:31:35 +01:00
  • 9e692967c3 fix(llama-cpp): Pass parameters when using embedded template (#8590) Richard Palethorpe 2026-02-17 17:50:05 +00:00
  • ecba23d44e fix: improve watchdown logics (#8591) Ettore Di Giacinto 2026-02-17 18:49:22 +01:00
  • 067a255435 chore: ⬆️ Update ggml-org/llama.cpp to d612901116ab2066c7923372d4827032ff296bc4 (#8588) LocalAI [bot] 2026-02-17 00:57:32 +01:00
  • 637ecba382 chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.2.0 to 1.3.0 (#8585) dependabot[bot] 2026-02-16 23:04:19 +00:00
  • 46c64e59f5 chore(deps): bump github.com/jaypipes/ghw from 0.22.0 to 0.23.0 (#8587) dependabot[bot] 2026-02-16 21:49:41 +00:00
  • f806838c37 chore(deps): bump google.golang.org/grpc from 1.78.0 to 1.79.1 (#8583) dependabot[bot] 2026-02-16 20:20:30 +00:00
  • 074a982853 fix(gallery): Use YAML v3 to avoid merging maps with incompatible keys (#8580) Richard Palethorpe 2026-02-16 13:10:19 +00:00
  • 109f29cc24 chore: ⬆️ Update ggml-org/llama.cpp to 27b93cbd157fc4ad94573a1fbc226d3e18ea1bb4 (#8577) LocalAI [bot] 2026-02-15 23:42:36 +01:00
  • 587e4a21b3 chore: ⬆️ Update antirez/voxtral.c to 134d366c24d20c64b614a3dcc8bda2a6922d077d (#8578) LocalAI [bot] 2026-02-15 23:42:11 +01:00
  • 3f1f58b2ab chore: ⬆️ Update ggml-org/whisper.cpp to 364c77f4ca2737e3287652e0e8a8c6dce3231bba (#8576) LocalAI [bot] 2026-02-15 22:20:04 +01:00
  • 01eb70caff Fix formatting in README.md for Audio to Text section Ettore Di Giacinto 2026-02-15 09:57:50 +01:00
  • d784851337 chore: ⬆️ Update ggml-org/llama.cpp to 01d8eaa28d57bfc6d06e30072085ed0ef12e06c5 (#8567) LocalAI [bot] 2026-02-14 22:52:32 +01:00
  • 1c4e5aa5c0 chore: bump cogito (#8568) Ettore Di Giacinto 2026-02-14 22:52:22 +01:00
  • 94df096fb9 fix: pin neutts-air to known working commit (#8566) LocalAI [bot] 2026-02-14 21:16:37 +01:00
  • 820bd7dd01 fix(ci): try to fix deps for l4t13 on qwen-* Ettore Di Giacinto 2026-02-14 10:21:23 +01:00
  • 42cb7bda19 fix(llama-cpp): populate tensor_buft_override buffer so llama-cpp properly performs fit calculations (#8560) Austen 2026-02-14 03:07:37 -06:00
  • 2fb9940b8a fix(voxcpm): pin setuptools (#8556) Ettore Di Giacinto 2026-02-13 23:44:35 +01:00
  • 2ff0ad4190 chore: ⬆️ Update ggml-org/llama.cpp to 05a6f0e8946914918758db767f6eb04bc1e38507 (#8553) LocalAI [bot] 2026-02-13 22:48:01 +01:00
  • bd12103ed4 chore: compute capabilities once (#8555) Ettore Di Giacinto 2026-02-13 22:23:06 +01:00
  • 2e17edd72a fix: prevent excessive logging in capability detection (#8552) LocalAI [bot] 2026-02-13 21:00:29 +01:00
  • 24aab68b3f feat(gallery): Add nanbeige4.1-3b (#8551) Richard Palethorpe 2026-02-13 17:23:44 +00:00
  • 5bdbb10593 fix(realtime): Send proper image data to backend (#8547) Richard Palethorpe 2026-02-13 17:01:07 +00:00
  • 1f0110368d step-flash fixes fix/step-flash-toolcall Ettore Di Giacinto 2026-02-12 23:35:44 +01:00
  • 2fd026e958 fix: update moonshine API, add setuptools to voxcpm requirements (#8541) Ettore Di Giacinto 2026-02-12 23:22:37 +01:00
  • 08718b656e chore: ⬆️ Update ggml-org/llama.cpp to 338085c69e486b7155e5b03d7b5087e02c0e2528 (#8538) LocalAI [bot] 2026-02-12 23:21:53 +01:00
  • 7121b189f7 chore(model-gallery): ⬆️ update checksum (#8540) LocalAI [bot] 2026-02-12 21:54:33 +01:00
  • f6c80a6987 feat(realtime): Allow sending text, image and audio conversation items" (#8524) Richard Palethorpe 2026-02-12 19:33:46 +00:00
  • 4a4d65f8e8 chore(model gallery): add vllm-omni models (#8536) Ettore Di Giacinto 2026-02-12 18:27:20 +01:00
  • 2858e71606 chore(model gallery): add neutts (#8535) Ettore Di Giacinto 2026-02-12 18:17:03 +01:00
  • 088205339c chore(model gallery): add voxcpm, whisperx, moonshine-tiny (#8534) Ettore Di Giacinto 2026-02-12 18:13:03 +01:00
  • 8616397d59 chore(model gallery): add nemo-asr (#8533) Ettore Di Giacinto 2026-02-12 18:01:42 +01:00
  • 1698f92bd0 Remove URL entry from gallery index Ettore Di Giacinto 2026-02-12 17:50:13 +01:00
  • 02c95a57ae Add known use cases for audio processing Ettore Di Giacinto 2026-02-12 17:49:54 +01:00
  • 2ab6be1d0c chore(model gallery): Add npc-llm-3-8b (#8498) rampa3 2026-02-12 17:46:25 +01:00
  • 9d78ec1bd8 chore(model gallery): add voxtral (which is only available in development) (#8532) Ettore Di Giacinto 2026-02-12 17:44:24 +01:00
  • b10b85de52 chore: improve log levels verbosity (#8528) LocalAI [bot] 2026-02-12 16:24:46 +01:00
  • 1479bee894 fix(realtime): Sampling and websocket locking (#8521) Richard Palethorpe 2026-02-12 12:57:34 +00:00
  • cff972094c feat(diffusers): add experimental support for sd_embed-style prompt embedding (#8504) Austen 2026-02-11 15:58:19 -06:00
  • 79a25f7ae9 chore: ⬆️ Update ggml-org/llama.cpp to 4d3daf80f8834e0eb5148efc7610513f1e263653 (#8513) LocalAI [bot] 2026-02-11 22:48:39 +01:00
  • 7270a98ce5 fix(realtime): Use user provided voice and allow pipeline models to have no backend (#8415) Richard Palethorpe 2026-02-11 13:18:05 +00:00
  • 0ee92317ec chore: ⬆️ Update ggml-org/llama.cpp to 57487a64c88c152ac72f3aea09bd1cc491b2f61e (#8499) LocalAI [bot] 2026-02-10 22:32:46 +01:00
  • 743d2d1947 chore: ⬆️ Update ggml-org/whisper.cpp to 764482c3175d9c3bc6089c1ec84df7d1b9537d83 (#8478) LocalAI [bot] 2026-02-10 15:14:59 +01:00
  • df04843f34 chore: ⬆️ Update ggml-org/llama.cpp to 262364e31d1da43596fe84244fba44e94a0de64e (#8479) LocalAI [bot] 2026-02-10 15:14:33 +01:00
  • 780877d1d0 security: validate URLs to prevent SSRF in content fetching endpoints (#8476) Kolega.dev 2026-02-10 14:14:14 +00:00
  • 08eeed61f4 chore(deps): bump github.com/openai/openai-go/v3 from 3.17.0 to 3.19.0 (#8485) dependabot[bot] 2026-02-10 05:41:15 +00:00
  • 5207ff84dc chore(deps): bump github.com/alecthomas/kong from 1.13.0 to 1.14.0 (#8481) dependabot[bot] 2026-02-10 04:29:00 +00:00
  • 4ade2e61ab chore(deps): bump github.com/onsi/ginkgo/v2 from 2.28.0 to 2.28.1 (#8483) dependabot[bot] 2026-02-10 03:15:46 +00:00
  • 818be98314 chore(deps): bump github.com/jaypipes/ghw from 0.21.2 to 0.22.0 (#8484) dependabot[bot] 2026-02-10 02:02:38 +00:00
  • 056c438452 chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.20.0 to 1.22.0 (#8482) dependabot[bot] 2026-02-09 23:34:36 +00:00
  • 0c040beb59 chore: ⬆️ Update antirez/voxtral.c to c9e8773a2042d67c637fc492c8a655c485354080 (#8477) LocalAI [bot] 2026-02-09 22:20:03 +01:00
  • bf5a1dd840 feat(voxtral): add voxtral backend (#8451) Ettore Di Giacinto 2026-02-09 09:12:05 +01:00
  • f44200bec8 chore(model gallery): Add Ministral 3 family of models (aside from base versions) (#8467) rampa3 2026-02-09 09:10:37 +01:00
  • 3b1b08efd6 chore: ⬆️ Update ggml-org/llama.cpp to e06088da0fa86aa444409f38dff274904931c507 (#8464) LocalAI [bot] 2026-02-09 09:09:32 +01:00
  • 3d8791067f chore: ⬆️ Update ggml-org/whisper.cpp to 4b23ff249e7f93137cb870b28fb27818e074c255 (#8463) LocalAI [bot] 2026-02-09 09:08:55 +01:00
  • da8207b73b feat(stablediffusion-ggml): Improve legacy CPU support for stablediffusion-ggml backend (#8461) Austen 2026-02-08 17:11:33 -06:00
  • aa9ca401fa docs: update model gallery documentation to reference main repository (#8452) Varun Chawla 2026-02-08 13:14:23 -08:00
  • e43c0c3ffc docs: ⬆️ update docs version mudler/LocalAI (#8462) LocalAI [bot] 2026-02-08 22:12:50 +01:00
  • 944874d08b chore: ⬆️ Update ggml-org/llama.cpp to 8872ad2125336d209a9911a82101f80095a9831d (#8448) v3.11.0 LocalAI [bot] 2026-02-07 22:22:18 +01:00
  • 3370d807c2 feat(nemo): add Nemo (only asr for now) backend (#8436) Ettore Di Giacinto 2026-02-07 08:19:37 +01:00
  • ae2689936a chore: ⬆️ Update ggml-org/llama.cpp to b83111815e9a79949257e9d4b087206b320a3063 (#8434) LocalAI [bot] 2026-02-06 22:22:33 +01:00
  • 15c12674b6 fix(qwen-asr): Remove contagious slop (DEFAULT_GOAL) from Makefile (#8431) Richard Palethorpe 2026-02-06 16:12:45 +00:00
  • 7fbe1d2e72 chore(models): Add Qwen TTS 0.6b (#8428) Richard Palethorpe 2026-02-06 09:30:36 +00:00
  • c1d0b10b14 chore(docs): Document using a local model gallery (#8426) Richard Palethorpe 2026-02-06 09:28:41 +00:00
  • efd552f83e fix(api)!: Stop model prior to deletion (#8422) Andres 2026-02-06 09:22:10 +01:00
  • bcd927da6e chore: ⬆️ Update ggml-org/llama.cpp to 22cae832188a1f08d18bd0a707a4ba5cd03c7349 (#8419) LocalAI [bot] 2026-02-06 09:21:33 +01:00
  • 682ac7e637 chore(model-gallery): ⬆️ update checksum (#8420) LocalAI [bot] 2026-02-05 21:34:26 +01:00
  • c8d74d35df feat(swagger): update swagger (#8418) LocalAI [bot] 2026-02-05 21:33:44 +01:00
  • a849f285a5 chore(tests): add audio/wav to expected wav file Ettore Di Giacinto 2026-02-05 20:27:06 +00:00
  • 697f6aa71c feat(audio): set audio content type (#8416) Ettore Di Giacinto 2026-02-05 19:14:12 +01:00
  • 218d0526cb fix(qwen-tts): add six dependency Ettore Di Giacinto 2026-02-05 18:05:31 +01:00
  • 9bc5ab18fa fix(voxcpm): make sed call unix-compliant Ettore Di Giacinto 2026-02-05 17:15:58 +01:00
  • a9267f391c fix(huggingface): add clean target Ettore Di Giacinto 2026-02-05 16:54:41 +01:00
  • 029ae3420d fix(package.sh): drop redundant -a and -R Ettore Di Giacinto 2026-02-05 16:39:33 +01:00
  • c0461f32a1 fix: add missing clean targets Ettore Di Giacinto 2026-02-05 16:38:16 +01:00
  • 8989d2944e fix: add clean target to local-store Ettore Di Giacinto 2026-02-05 14:55:34 +01:00
  • 7aea2add44 Revert "chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/rerankers in the pip group across 1 directory" (#8412) Ettore Di Giacinto 2026-02-05 14:17:33 +01:00
  • 55e43b3f92 chore(deps): bump torch from 2.4.1 to 2.7.1+xpu in /backend/python/rerankers in the pip group across 1 directory (#8407) dependabot[bot] 2026-02-05 12:37:52 +00:00