Commit Graph

  • c8d63a1003 fix(react-ui): stop Manage page from blanking on auto-refresh; show real model use cases Ettore Di Giacinto 2026-04-26 19:34:54 +00:00
  • d9cb0d6133 chore: ⬆️ Update ggml-org/llama.cpp to dcad77cc3b0865153f486327064fb0320a57a476 (#9572) LocalAI [bot] 2026-04-26 12:38:35 +02:00
  • f5c268deac chore: ⬆️ Update TheTom/llama-cpp-turboquant to 11a241d0db78a68e0a5b99fe6f36de6683100f6a (#9571) LocalAI [bot] 2026-04-26 12:38:25 +02:00
  • 8931a2ad31 fix(gallery): normalize inconsistent tag casing/plurals across gallery models (#9574) Tai An 2026-04-25 23:33:38 -07:00
  • e16e758dff ci(backends): build cpu-whisperx and cpu-faster-whisper for linux/arm64 (#9573) Ettore Di Giacinto 2026-04-26 08:30:03 +02:00
  • 1c45227346 chore: ⬆️ Update ikawrakow/ik_llama.cpp to 3a945af45d45936341a45bbf7deda56776a4af26 (#9570) LocalAI [bot] 2026-04-26 08:26:37 +02:00
  • fbe4f0a99b fix(docs): replace Docsy alert shortcode with Relearn notice Ettore Di Giacinto 2026-04-25 21:04:31 +00:00
  • d733c9cd13 fix(mlx-vlm): pin upstream to v0.4.4 to unblock CUDA builds (#9568) Ettore Di Giacinto 2026-04-25 22:06:01 +02:00
  • 703b4fcae8 Change cron schedule to run every 12 hours Ettore Di Giacinto 2026-04-25 18:38:28 +02:00
  • 73aacad2f9 fix(vllm): drop flash-attn wheel to avoid torch 2.10 ABI mismatch (#9557) Richard Palethorpe 2026-04-25 16:38:13 +01:00
  • 806ea24ff4 chore: ⬆️ Update TheTom/llama-cpp-turboquant to 67559e580b10e4e47e9a6fd6218873997976886d (#9497) LocalAI [bot] 2026-04-25 14:03:46 +02:00
  • 385de3705e chore(model gallery): 🤖 add 1 new models via gallery agent (#9558) LocalAI [bot] 2026-04-25 14:03:15 +02:00
  • 21eace40ec feat(llama-cpp): expose split_mode option for multi-GPU placement (#9560) Ettore Di Giacinto 2026-04-25 14:02:57 +02:00
  • 24505e57f5 feat(backends): add CUDA 13 + L4T arm64 CUDA 13 variants for vllm/vllm-omni/sglang (#9553) Ettore Di Giacinto 2026-04-25 12:26:29 +02:00
  • d09706dc60 chore(model gallery): 🤖 add 1 new models via gallery agent (#9555) LocalAI [bot] 2026-04-25 09:00:37 +02:00
  • 08e393f7db chore: ⬆️ Update ikawrakow/ik_llama.cpp to cb58a561f0c49f68b6d125cdfda037ed80433821 (#9549) LocalAI [bot] 2026-04-25 08:59:48 +02:00
  • 47cc3dc8d7 chore: ⬆️ Update ggml-org/llama.cpp to 361fe72acb7b9bd79059cc177cbeda99b35b5db9 (#9548) LocalAI [bot] 2026-04-25 08:58:27 +02:00
  • 83b384de97 feat: surface distributed backend management errors (#9552) Ettore Di Giacinto 2026-04-25 08:57:59 +02:00
  • 487e3fd2a4 feat(react-ui): editorial refresh with Nord palette and polished primitives (#9550) Ettore Di Giacinto 2026-04-24 23:35:59 +02:00
  • 9787bee48b fix(buun-llama-cpp): shim cudaMemcpy{To,From}Symbol + WARP_SIZE on fwht128 shuffles feat/buun-llama-cpp-backend Ettore Di Giacinto 2026-04-24 20:09:36 +00:00
  • 9ab3496de2 chore(deps): bump rustls-webpki from 0.103.10 to 0.103.13 in /backend/rust/kokoros in the cargo group across 1 directory (#9546) dependabot[bot] 2026-04-24 22:02:58 +02:00
  • c4511be33a chore(deps): bump postcss from 8.5.8 to 8.5.10 in /core/http/react-ui in the npm_and_yarn group across 1 directory (#9544) dependabot[bot] 2026-04-24 22:02:41 +02:00
  • 551ebdb57a fix(distributed): correct VRAM/RAM reporting on NVIDIA unified-memory hosts (#9545) Ettore Di Giacinto 2026-04-24 22:02:23 +02:00
  • 1d0de757c3 fix: add hipblaslt library (#9541) Andreas Egli 2026-04-24 18:50:03 +02:00
  • 42754d33b9 fix(buun-llama-cpp): pass WARP_SIZE to argmax __shfl_xor_sync calls Ettore Di Giacinto 2026-04-24 16:29:29 +00:00
  • e5337039b0 [intel GPU support] Use latest oneapi-basekit image for Intel images to support b70 (#9543) Alex Brick 2026-04-24 11:29:10 -05:00
  • 7f2b7e4ace fix(buun-llama-cpp): shim atomicAdd(double*,double) for pre-sm_60 CUDA Ettore Di Giacinto 2026-04-24 13:57:30 +00:00
  • 1c9592c77f chore: ⬆️ Update leejet/stable-diffusion.cpp to b8bdffc19962be7e5a84bfefeb2e31bd885b571a (#9521) LocalAI [bot] 2026-04-24 15:15:15 +02:00
  • 6233feb190 ci(buun-llama-cpp): wire backend into test-extra + build matrix Ettore Di Giacinto 2026-04-24 12:52:44 +00:00
  • d6bf3a4969 fix(buun-llama-cpp): drop logit_bias_eog arg from params_from_json_cmpl Ettore Di Giacinto 2026-04-24 11:16:29 +00:00
  • b27d38a53d fix(buun-llama-cpp): backport logit_bias_eog field to grpc-server copy Ettore Di Giacinto 2026-04-24 11:12:51 +00:00
  • 45756b19dc test(gallery): extend importer specs to cover buun-llama-cpp Ettore Di Giacinto 2026-04-24 11:08:37 +00:00
  • cd6079b2f3 feat(backend): add buun-llama-cpp fork (DFlash + TCQ KV-cache) Ettore Di Giacinto 2026-04-24 08:05:21 +00:00
  • 3db60b57e6 fix(realtime): consume ChatDeltas when C++ autoparser clears Response (#9538) Richard Palethorpe 2026-04-24 13:41:38 +01:00
  • 13734ae9fa feat: Add Sherpa ONNX backend for ASR and TTS (#8523) Richard Palethorpe 2026-04-24 13:40:06 +01:00
  • c0920f3273 fix(ik-llama-cpp): patch clip.cpp for new ggml_quantize_chunk signature (#9531) Ettore Di Giacinto 2026-04-24 13:07:26 +02:00
  • 7c1934b183 chore: ⬆️ Update ggml-org/llama.cpp to 187a45637054881ecacf17f8e2f6f8f2ba7df1c7 (#9520) LocalAI [bot] 2026-04-24 09:17:06 +02:00
  • 5e062b4d1f fix: use SetFunctionCallNameString when forcing a specific tool (3 sites) (#9526) Tai An 2026-04-24 00:06:42 -07:00
  • 4906cbad04 feat: add biometrics UI (#9524) Ettore Di Giacinto 2026-04-24 08:50:34 +02:00
  • c755cd5ab5 feat(swagger): update swagger (#9518) LocalAI [bot] 2026-04-23 23:26:50 +02:00
  • 0fb04f7ac3 chore(model-gallery): ⬆️ update checksum (#9522) LocalAI [bot] 2026-04-23 23:26:27 +02:00
  • d9d7b5c29b docs(readme): add April 2026 highlights to Latest News docs/readme-april-news Ettore Di Giacinto 2026-04-23 20:47:06 +00:00
  • f877942d97 fix(openresponses): parse OpenAI-spec nested tool_choice + use correct setter (#9509) walcz-de 2026-04-23 18:30:05 +02:00
  • f5eb13d3c2 feat(insightface): add antispoofing (liveness) detection (#9515) Ettore Di Giacinto 2026-04-23 18:28:15 +02:00
  • c1f923b2bc fix(importer): emit all shards for multi-part GGUF models (#9513) Ettore Di Giacinto 2026-04-23 15:00:02 +02:00
  • ed648b3b4e fix(llama-cpp): include server-chat.cpp in grpc-server translation unit (#9511) Ettore Di Giacinto 2026-04-23 14:59:39 +02:00
  • 3ce5248126 Update expected length of instructions in test Ettore Di Giacinto 2026-04-23 14:58:57 +02:00
  • 04f1a0285d fix(ik-llama-cpp): adapt to common_grammar struct in sampling.h (#9512) Ettore Di Giacinto 2026-04-23 13:45:06 +02:00
  • 181ebb6df4 feat: voice recognition (#9500) Ettore Di Giacinto 2026-04-23 12:07:14 +02:00
  • 1c59165d63 chore(model gallery): 🤖 add 1 new models via gallery agent (#9505) LocalAI [bot] 2026-04-23 09:32:44 +02:00
  • eb00d9b178 chore: ⬆️ Update leejet/stable-diffusion.cpp to c97702e1057c2fe13a7074cd9069cb9dd6edc1bf (#9495) LocalAI [bot] 2026-04-23 09:32:21 +02:00
  • 2068b6f43c feat(swagger): update swagger (#9498) LocalAI [bot] 2026-04-22 22:51:39 +02:00
  • eb01c77214 fix(kokoros): implement face_verify and face_analyze trait stubs (#9499) Ettore Di Giacinto 2026-04-22 22:51:18 +02:00
  • bb4fda6f0e chore(agents): Update the backend creation instructions to include Rust and extra tests (#9490) Richard Palethorpe 2026-04-22 21:43:01 +01:00
  • f0c92610a1 feat(importer): expand importer flow to almost all backends (#9466) Ettore Di Giacinto 2026-04-22 22:42:37 +02:00
  • 5f7a0c3b26 chore(turboquant): bump fork pin to rebase/upstream-sync-april-2026 bump/turboquant-upstream-sync-april-2026 Ettore Di Giacinto 2026-04-22 20:01:49 +00:00
  • bbeacf140d fix: remove unsafe sprintf() in grpc-server.cpp (#9486) orbisai0security 2026-04-23 01:27:29 +05:30
  • 6820ec468f chore(model gallery): 🤖 add 1 new models via gallery agent (#9491) LocalAI [bot] 2026-04-22 21:56:11 +02:00
  • 20baec77ab feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480) Ettore Di Giacinto 2026-04-22 21:55:41 +02:00
  • d16f19f1eb fix(kokoros): Build and publish the backend images from CI/CD (#9487) Richard Palethorpe 2026-04-22 12:19:55 +01:00
  • 9eb21e9a20 fix(turboquant): patch ggml-hip CMakeLists to compile new f16-turbo fattn-vec instances update/TURBOQUANT_VERSION Ettore Di Giacinto 2026-04-22 07:17:33 +00:00
  • 798b5b2d84 chore(turboquant): bump fork to 4d24ad87 and patch ggml-hip for new f16-turbo fattn-vec instances issue-9478-turboquant-update Ettore Di Giacinto 2026-04-22 07:13:47 +00:00
  • cd7b035716 chore: ⬆️ Update ggml-org/llama.cpp to 5a4cd6741fc33227cdacb329f355ab21f8481de2 (#9479) LocalAI [bot] 2026-04-22 08:58:19 +02:00
  • 0f3bb2d647 chore(model gallery): 🤖 add 1 new models via gallery agent (#9481) LocalAI [bot] 2026-04-22 08:22:05 +02:00
  • 85ff7a310f ⬆️ Update TheTom/llama-cpp-turboquant mudler 2026-04-21 21:28:32 +00:00
  • 607efe5a4c fix(backend-monitor): accept model as a query parameter (#9411) Adira 2026-04-21 23:06:35 +03:00
  • 7d8c1d5e45 fix(streaming): dedupe content, recover reasoning, unique tool_call IDs in deferred flush (#9470) Ettore Di Giacinto 2026-04-21 21:59:33 +02:00
  • d18d434bb2 Respect explicit reasoning config during GGUF thinking probe (#9463) leinasi2014 2026-04-22 03:53:10 +08:00
  • 39573ecd2a chore(whisperx): drop ROCm/hipblas build target (#9474) Ettore Di Giacinto 2026-04-21 21:50:18 +02:00
  • a7dbb2a83d fix(gallery-agent): process blacklist command on recently-closed PRs (#9473) Ettore Di Giacinto 2026-04-21 16:29:13 +02:00
  • 3ad9b16c29 chore(deps): bump github.com/coreos/go-oidc/v3 from 3.17.0 to 3.18.0 (#9455) dependabot[bot] 2026-04-21 15:31:02 +02:00
  • c806d5ab73 chore(deps): bump github.com/aws/aws-sdk-go-v2/config from 1.32.14 to 1.32.16 (#9456) dependabot[bot] 2026-04-21 15:30:22 +02:00
  • 47efaf5b43 Fix: Add model parameter to neutts-air gallery definition (#8793) LocalAI [bot] 2026-04-21 11:56:00 +02:00
  • 315b634a91 feat: improve CLI error messages with actionable guidance (#8880) LocalAI [bot] 2026-04-21 11:53:26 +02:00
  • 6b245299d7 chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.4.1 to 1.5.0 (#9454) dependabot[bot] 2026-04-21 11:43:00 +02:00
  • 677c0315c1 chore(deps): bump github.com/containerd/containerd from 1.7.30 to 1.7.31 (#9453) dependabot[bot] 2026-04-21 11:42:43 +02:00
  • 478522ce4d chore(deps): bump github.com/aws/aws-sdk-go-v2/service/s3 from 1.97.1 to 1.99.1 (#9452) dependabot[bot] 2026-04-21 11:42:27 +02:00
  • c54897ad44 fix(tests): update InstallBackend call sites for new URI/Name/Alias params (#9467) Ettore Di Giacinto 2026-04-21 11:41:38 +02:00
  • 8bb1e8f21f chore: ⬆️ Update ggml-org/llama.cpp to cf8b0dbda9ac0eac30ee33f87bc6702ead1c4664 (#9448) LocalAI [bot] 2026-04-21 11:15:45 +02:00
  • cd94a0b61a chore: ⬆️ Update ggml-org/whisper.cpp to fc674574ca27cac59a15e5b22a09b9d9ad62aafe (#9450) LocalAI [bot] 2026-04-21 11:09:05 +02:00
  • 047bc48fa9 chore(model gallery): 🤖 add 1 new models via gallery agent (#9464) LocalAI [bot] 2026-04-21 11:07:07 +02:00
  • 01bd8ae5d0 [gallery] Fix duplicate sha256 keys in Wan models (#9461) sec171 2026-04-21 05:06:36 -04:00
  • d9808769be chore(model-gallery): ⬆️ update checksum (#9451) LocalAI [bot] 2026-04-21 00:07:58 +02:00
  • 5973c0a9df chore: ⬆️ Update ikawrakow/ik_llama.cpp to d4824131580b94ffa7b0e91c955e2b237c2fe16e (#9447) LocalAI [bot] 2026-04-21 00:07:19 +02:00
  • 486b5e25a3 fix(config): ignore yaml backup files in model loader (#9443) leinasi2014 2026-04-21 05:41:39 +08:00
  • c66c41e8d7 fix(ci): wire AMDGPU_TARGETS through backend build workflow (#9445) Russell Sim 2026-04-20 23:41:19 +02:00
  • 02bb715c0a fix(distributed): pass ExternalURI through NATS backend install (#9446) Russell Sim 2026-04-20 23:39:35 +02:00
  • 8ab56e2ad3 feat(gallery): add wan i2v 720p (#9457) Ettore Di Giacinto 2026-04-20 23:34:11 +02:00
  • ecf85fde9e fix(api): remove duplicate /api/traces endpoint that broke React UI (#9427) pjbrzozowski 2026-04-20 18:44:49 +02:00
  • 6480715a16 fix(settings): strip env-supplied ApiKeys from the request before persisting (#9438) Sai Asish Y 2026-04-20 01:36:54 -07:00
  • f683231811 feat(gallery): add Wan 2.1 FLF2V 14B 720P (#9440) Ettore Di Giacinto 2026-04-20 10:34:36 +02:00
  • 960757f0e8 chore(model gallery): 🤖 add 1 new models via gallery agent (#9436) LocalAI [bot] 2026-04-20 08:48:47 +02:00
  • 865fd552f5 docs(agents): adopt kernel's AI coding assistants policy Ettore Di Giacinto 2026-04-19 22:50:54 +00:00
  • cb77a5a4b9 chore(model gallery): 🤖 add 1 new models via gallery agent (#9425) LocalAI [bot] 2026-04-20 00:42:44 +02:00
  • 60633c4dd5 fix(stable-diffusion.ggml): force mp4 container in ffmpeg mux (#9435) Ettore Di Giacinto 2026-04-20 00:41:54 +02:00
  • 9e44944cc1 fix(i2v): Add new options to the model configuration Ettore Di Giacinto 2026-04-20 00:27:05 +02:00
  • 372eb08dcf fix(gallery): allow uninstalling orphaned meta backends + force reinstall (#9434) Ettore Di Giacinto 2026-04-20 00:10:19 +02:00
  • 28091d626e chore: ⬆️ Update ikawrakow/ik_llama.cpp to 00ba208a5c036eee72d4a631b4f57c126095cb03 (#9430) LocalAI [bot] 2026-04-20 00:01:48 +02:00
  • cae79d9107 feat(swagger): update swagger (#9431) LocalAI [bot] 2026-04-19 23:39:50 +02:00
  • babbbc6ec8 chore: ⬆️ Update ggml-org/llama.cpp to 4eac5b45095a4e8a1ff1cce4f6d030e0872fb4ad (#9429) LocalAI [bot] 2026-04-19 23:39:19 +02:00