Commit Graph

  • fdc2c0737c chore: ⬆️ Update ggml-org/llama.cpp to 593da7fa49503b68f9f01700be9f508f1e528992 (#7946) LocalAI [bot] 2026-01-09 22:13:04 +01:00
  • f4b0a304d7 chore(llama.cpp): propagate errors during model load (#7937) Ettore Di Giacinto 2026-01-09 07:52:49 +01:00
  • d16ec7aa9e chore(deps): Bump llama.cpp to '480160d47297df43b43746294963476fc0a6e10f' (#7933) Ettore Di Giacinto 2026-01-09 07:52:32 +01:00
  • d699b7ccdc Add backend configuration for Granite embedding model Ettore Di Giacinto 2026-01-09 00:44:10 +01:00
  • a4d224dd1b Revert "chore(uv): add --index-strategy=unsafe-first-match to l4t" (#7936) Ettore Di Giacinto 2026-01-08 23:31:51 +01:00
  • 917c7aa9f3 chore(ci): roll back l4t-cuda12 configurations (#7935) Ettore Di Giacinto 2026-01-08 23:04:33 +01:00
  • 5aa66842dd chore: ⬆️ Update leejet/stable-diffusion.cpp to 0e52afc6513cc2dea9a1a017afc4a008d5acf2b0 (#7930) LocalAI [bot] 2026-01-08 22:48:46 +01:00
  • f5dee90962 chore(uv): add --index-strategy=unsafe-first-match to l4t (#7934) Ettore Di Giacinto 2026-01-08 22:48:03 +01:00
  • 856d90400a chore(uv): add --index-strategy=unsafe-first-match to l4t fix/ci-503s Ettore Di Giacinto 2026-01-08 21:47:16 +00:00
  • 06323df457 Optimize GPU library copying to preserve symlinks and avoid duplicates (#7931) Copilot 2026-01-08 22:26:48 +01:00
  • 98f28bf583 chore(docs): Add Crush and VoxInput to the integrations (#7924) Richard Palethorpe 2026-01-08 20:39:25 +00:00
  • 383312b50e chore(l4t-12): do not use python 3.12 (wheels are only for 3.10) (#7928) Ettore Di Giacinto 2026-01-08 19:00:07 +01:00
  • b736db4bbe chore(ci): use latest jetpack image for l4t (#7926) Ettore Di Giacinto 2026-01-08 18:30:59 +01:00
  • 09bc2e4a00 chore(model gallery): 🤖 add 1 new models via gallery agent (#7922) LocalAI [bot] 2026-01-08 11:06:21 +01:00
  • c03e532a18 chore: ⬆️ Update ggml-org/llama.cpp to ae9f8df77882716b1702df2bed8919499e64cc28 (#7915) LocalAI [bot] 2026-01-07 23:24:01 +01:00
  • fcb58ee243 fix(intel): Add ARG for Ubuntu codename in Dockerfile (#7917) Ettore Di Giacinto 2026-01-07 21:55:18 +01:00
  • b2ff1cea2a feat: enable Vulkan arm64 image builds (#7912) Copilot 2026-01-07 21:49:50 +01:00
  • b964b3d53e feat(backends): add moonshine backend for faster transcription (#7833) Ettore Di Giacinto 2026-01-07 21:44:35 +01:00
  • 0b26669d0b chore(model gallery): 🤖 add 1 new models via gallery agent (#7916) LocalAI [bot] 2026-01-07 21:43:39 +01:00
  • 5a9698bc69 chore(Dockerfile): restore GPU vendor specific sections (#7911) Ettore Di Giacinto 2026-01-07 16:34:23 +01:00
  • 1fe0e9f74f chore(ci): restore building of GPU vendor images (#7910) Ettore Di Giacinto 2026-01-07 16:32:22 +01:00
  • ffb2dc4666 chore(detection): detect GPU vendor from files present in the system (#7908) Ettore Di Giacinto 2026-01-07 16:18:27 +01:00
  • cfc2225fc7 chore(dockerfile): drop driver-requirements section (#7907) Ettore Di Giacinto 2026-01-07 16:18:14 +01:00
  • fd53978a7b feat: package GPU libraries inside backend containers for unified base image (#7891) Copilot 2026-01-07 15:48:51 +01:00
  • 7abc0242bb chore(model gallery): 🤖 add 1 new models via gallery agent (#7903) LocalAI [bot] 2026-01-07 09:46:36 +01:00
  • 23df29fbd3 chore: ⬆️ Update leejet/stable-diffusion.cpp to 9be0b91927dfa4007d053df72dea7302990226bb (#7895) LocalAI [bot] 2026-01-06 22:18:53 +01:00
  • fb9879949c chore: ⬆️ Update ggml-org/llama.cpp to ccbc84a5374bab7a01f68b129411772ddd8e7c79 (#7894) LocalAI [bot] 2026-01-06 22:18:35 +01:00
  • 1642b39cb8 [gallery] add JSON schema for gallery model specification (#7890) Manish Dewangan 2026-01-07 02:40:43 +05:30
  • e6ba26c3e7 chore: Update to Ubuntu24.04 (cont #7423) (#7769) Richard Palethorpe 2026-01-06 14:26:42 +00:00
  • 26c4f80d1b chore(llama.cpp/flags): simplify conditionals (#7887) Ettore Di Giacinto 2026-01-06 15:02:20 +01:00
  • 5add7b47f5 fix: BMI2 crash on AVX-only CPUs (Intel Ivy Bridge/Sandy Bridge) (#7864) coffeerunhobby 2026-01-06 02:13:48 +02:00
  • 3244ccc224 chore(image-ui): simplify interface (#7882) Ettore Di Giacinto 2026-01-05 23:20:28 +01:00
  • 4f7b6b0bff chore: ⬆️ Update ggml-org/llama.cpp to e443fbcfa51a8a27b15f949397ab94b5e87b2450 (#7881) LocalAI [bot] 2026-01-05 22:55:40 +01:00
  • 3a629cea2f chore: ⬆️ Update ggml-org/whisper.cpp to 679bdb53dbcbfb3e42685f50c7ff367949fd4d48 (#7879) LocalAI [bot] 2026-01-05 22:55:16 +01:00
  • f917feda29 chore: ⬆️ Update leejet/stable-diffusion.cpp to c5602a676caff5fe5a9f3b76b2bc614faf5121a5 (#7880) LocalAI [bot] 2026-01-05 22:54:56 +01:00
  • e2018cdc8f chore(deps): bump github.com/labstack/echo/v4 from 4.14.0 to 4.15.0 (#7875) dependabot[bot] 2026-01-05 22:54:30 +01:00
  • a3b8a94187 fix(ui): fix 404 on API menu link by pointing to index.html (#7878) Manish Dewangan 2026-01-06 03:24:14 +05:30
  • 41de7d32ad chore(deps): bump dependabot/fetch-metadata from 2.4.0 to 2.5.0 (#7876) dependabot[bot] 2026-01-05 20:10:07 +00:00
  • 93364df0a8 chore(AGENTS.md): Add section to help with building backends (#7871) Richard Palethorpe 2026-01-05 17:25:52 +00:00
  • 21c84f432f feat(function): Add tool streaming, XML Tool Call Parsing Support (#7865) Ettore Di Giacinto 2026-01-05 18:25:40 +01:00
  • 9d3da0bed5 chore: ⬆️ Update ggml-org/llama.cpp to 4974bf53cf14073c7b66e1151348156aabd42cb8 (#7861) LocalAI [bot] 2026-01-05 00:10:18 +01:00
  • 1b063b5595 chore: ⬆️ Update leejet/stable-diffusion.cpp to b90b1ee9cf84ea48b478c674dd2ec6a33fd504d6 (#7862) LocalAI [bot] 2026-01-04 23:52:01 +01:00
  • 93d3e4257a recursive fix/tools-null-properties Ettore Di Giacinto 2026-01-04 18:00:14 +00:00
  • e0e904ff98 fixups Ettore Di Giacinto 2026-01-04 17:40:48 +00:00
  • a95422f4d1 fix(tools): sanitize inputs Ettore Di Giacinto 2026-01-04 17:06:49 +00:00
  • 560bf50299 chore(Makefile): refactor common make targets (#7858) Ettore Di Giacinto 2026-01-04 21:12:50 +01:00
  • a7e155240b chore: ⬆️ Update ggml-org/llama.cpp to e57f52334b2e8436a94f7e332462dfc63a08f995 (#7848) LocalAI [bot] 2026-01-04 10:27:45 +01:00
  • 793e4907a2 feat(swagger): update swagger (#7847) LocalAI [bot] 2026-01-03 22:09:39 +01:00
  • d38811560c chore(docs): add opencode, GHA, and realtime voice assistant examples Ettore Di Giacinto 2026-01-03 22:03:43 +01:00
  • 33cc0b8e13 fix(chat/ui): record model name in history for consistency (#7845) Ettore Di Giacinto 2026-01-03 18:05:33 +01:00
  • 4cd95b8a9d fix: Highly inconsistent agent response to cogito agent calling MCP server - Body "Invalid http method" (#7790) lif 2026-01-03 22:43:23 +08:00
  • 8c504113a2 chore(model gallery): 🤖 add 1 new models via gallery agent (#7840) LocalAI [bot] 2026-01-03 08:42:05 +01:00
  • 666d110714 fix: Prevent BMI2 instruction crash on AVX-only CPUs (#7817) coffeerunhobby 2026-01-03 09:36:55 +02:00
  • 641606ae93 chore: ⬆️ Update ggml-org/llama.cpp to 706e3f93a60109a40f1224eaf4af0d59caa7c3ae (#7836) LocalAI [bot] 2026-01-02 22:26:37 +01:00
  • 2adddef5fe Address feedback from review fix/mcp Ettore Di Giacinto 2026-01-02 21:34:23 +01:00
  • d89c7b731a fix: resolve duplicate MCP route registration causing 50% failure rate majiayu000 2025-12-30 16:56:18 +08:00
  • 5f6c941399 fix(llama.cpp/mmproj): fix loading mmproj in nested sub-dirs different from model path (#7832) Ettore Di Giacinto 2026-01-02 20:17:30 +01:00
  • 1639fc6309 chore(model gallery): 🤖 add 1 new models via gallery agent (#7831) LocalAI [bot] 2026-01-02 15:10:00 +01:00
  • 841e8f6d47 fix(image-gen): fix scrolling issues (#7829) Ettore Di Giacinto 2026-01-02 09:05:49 +01:00
  • fd152c97c0 chore(model gallery): 🤖 add 1 new models via gallery agent (#7826) LocalAI [bot] 2026-01-02 08:45:43 +01:00
  • 949de04052 chore: ⬆️ Update ggml-org/llama.cpp to ced765be44ce173c374f295b3c6f4175f8fd109b (#7822) LocalAI [bot] 2026-01-02 08:44:49 +01:00
  • 76cfe1f367 feat(image-gen/UI): move controls to the left, make the page more compact (#7823) Ettore Di Giacinto 2026-01-01 22:07:42 +01:00
  • 5ee6c1810b feat(swagger): update swagger (#7820) LocalAI [bot] 2026-01-01 21:16:38 +01:00
  • 7db79aadfa chore(model-gallery): ⬆️ update checksum (#7821) LocalAI [bot] 2026-01-01 21:16:11 +01:00
  • dee48679b4 Fix(gallery): Updated checksums for qwen3-vl-30b instruct & thinking (#7819) nold 2026-01-01 19:33:55 +00:00
  • 94b47a9310 chore(model gallery): 🤖 add 1 new models via gallery agent (#7816) LocalAI [bot] 2026-01-01 19:20:26 +01:00
  • bc3e8793ed chore: ⬆️ Update ggml-org/llama.cpp to 13814eb370d2f0b70e1830cc577b6155b17aee47 (#7809) LocalAI [bot] 2025-12-31 23:04:01 +01:00
  • 91978bb3a5 chore: ⬆️ Update ggml-org/whisper.cpp to e9898ddfb908ffaa7026c66852a023889a5a7202 (#7810) LocalAI [bot] 2025-12-31 22:59:05 +01:00
  • 797f27f09f feat(UI): image generation improvements (#7804) Ettore Di Giacinto 2025-12-31 21:59:46 +01:00
  • 3f1631aa87 chore(model gallery): 🤖 add 1 new models via gallery agent (#7807) LocalAI [bot] 2025-12-31 19:29:59 +01:00
  • dad509637e chore(model gallery): 🤖 add 1 new models via gallery agent (#7801) LocalAI [bot] 2025-12-31 09:18:35 +01:00
  • 218f3a126a chore: ⬆️ Update ggml-org/llama.cpp to 0f89d2ecf14270f45f43c442e90ae433fd82dab1 (#7795) LocalAI [bot] 2025-12-31 08:53:41 +01:00
  • be77a845fa fix(gallery agent): change model Ettore Di Giacinto 2025-12-30 22:34:25 +00:00
  • ca32286022 fix(gallery agent): change model Ettore Di Giacinto 2025-12-30 22:27:48 +00:00
  • 1f592505dd fix(gallery agent): change model Ettore Di Giacinto 2025-12-30 22:22:45 +00:00
  • b3bc623eb3 fix(gallery agent): fixups Ettore Di Giacinto 2025-12-30 22:17:58 +00:00
  • e56391cf14 Add individual sponsors acknowledgment in README Ettore Di Giacinto 2025-12-30 23:01:22 +01:00
  • ef3ffe4a4e fix(gallery agent): fixups Ettore Di Giacinto 2025-12-30 21:56:54 +00:00
  • 3cffde2cd5 fix(gallery agent): skip model selection if only one Ettore Di Giacinto 2025-12-30 21:53:37 +00:00
  • 234bf7e2ad feat(swagger): update swagger (#7794) LocalAI [bot] 2025-12-30 22:05:01 +01:00
  • ba73d2e759 fix: Failed to download checksums.txt when using launch to install localai (#7788) lif 2025-12-31 01:33:44 +08:00
  • 592697216b Revert "chore(deps): bump securego/gosec from 2.22.9 to 2.22.11" (#7789) Ettore Di Giacinto 2025-12-30 09:58:13 +01:00
  • 8bd7143a44 fix: propagate validation errors (#7787) lif 2025-12-30 16:54:27 +08:00
  • 0d0ef0121c fix: Usage for image generation is incorrect (and causes error in LiteLLM) (#7786) lif 2025-12-30 16:53:05 +08:00
  • d7b2eee08f fix: add nil checks before mergo.Merge to prevent panic in gallery model installation (#7785) lif 2025-12-30 16:51:45 +08:00
  • bc8ec5cb39 chore: ⬆️ Update ggml-org/llama.cpp to c9a3b40d6578f2381a1373d10249403d58c3c5bd (#7778) LocalAI [bot] 2025-12-30 08:27:16 +01:00
  • 3f38fecdfc chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.1.0 to 1.2.0 (#7776) dependabot[bot] 2025-12-29 22:15:29 +01:00
  • 20a4199229 chore(deps): bump github.com/schollz/progressbar/v3 from 3.18.0 to 3.19.0 (#7775) dependabot[bot] 2025-12-29 22:15:11 +01:00
  • ded9955881 chore(ci): do not select models if we have only 1 result Ettore Di Giacinto 2025-12-29 22:14:14 +01:00
  • cf78f9a2a8 chore(deps): bump google.golang.org/grpc from 1.77.0 to 1.78.0 (#7777) dependabot[bot] 2025-12-29 21:03:57 +01:00
  • 0c16f55b45 chore(deps): bump securego/gosec from 2.22.9 to 2.22.11 (#7774) dependabot[bot] 2025-12-29 19:18:29 +00:00
  • 0b80167912 chore: ⬆️ Update leejet/stable-diffusion.cpp to 4ff2c8c74bd17c2cfffe3a01be77743fb3efba2f (#7771) Richard Palethorpe 2025-12-29 18:06:35 +00:00
  • 99b5c5f156 feat(api): Allow tracing of requests and responses (#7609) Richard Palethorpe 2025-12-29 10:06:06 +00:00
  • 9ab812a8e8 chore(ci): be more precise when detecting existing models (#7767) Ettore Di Giacinto 2025-12-29 10:06:42 +01:00
  • 185a685211 fix(amd-gpu): correctly show total and used vram (#7761) Ettore Di Giacinto 2025-12-29 07:57:07 +01:00
  • 1a6fd0f7fc chore: ⬆️ Update ggml-org/llama.cpp to 4ffc47cb2001e7d523f9ff525335bbe34b1a2858 (#7760) LocalAI [bot] 2025-12-28 22:10:39 +01:00
  • c95c482f36 chore: ⬆️ Update ggml-org/llama.cpp to a4bf35889eda36d3597cd0f8f333f5b8a2fcaefc (#7751) LocalAI [bot] 2025-12-27 22:09:12 +01:00
  • 21c464c34f fix(cli): import via CLI needs system state (#7746) Ettore Di Giacinto 2025-12-27 11:10:28 +01:00
  • ddf0281785 chore: ⬆️ Update ggml-org/llama.cpp to 7ac8902133da6eb390c4d8368a7d252279123942 (#7740) LocalAI [bot] 2025-12-26 22:44:34 +01:00
  • 86c68c9623 chore: ⬆️ Update ggml-org/llama.cpp to 85c40c9b02941ebf1add1469af75f1796d513ef4 (#7731) LocalAI [bot] 2025-12-25 22:10:28 +01:00