Commit Graph

  • ce33b7e6f8 docs: add comprehensive development setup instructions to CONTRIBUTING.md (H7) (#8860) LocalAI [bot] 2026-03-08 18:27:00 +01:00
  • 9090bca920 feat: Add documentation for undocumented API endpoints (#8852) LocalAI [bot] 2026-03-08 17:59:33 +01:00
  • ec8f2d7683 fix: Correct Talk Interface screenshot reference in README.md (H6) (#8857) LocalAI [bot] 2026-03-08 17:58:59 +01:00
  • ff02e7ff5b docs: clarify SECURITY.md version support table with specific ranges and EOL dates (#8861) LocalAI [bot] 2026-03-08 17:58:19 +01:00
  • 85e4871d4d chore: ⬆️ Update leejet/stable-diffusion.cpp to c8fb3d245858d495be1f140efdcfaa0d49de41e5 (#8841) LocalAI [bot] 2026-03-08 09:53:08 +01:00
  • 364ad30a2f feat(downloader): add HF_MIRROR environment variable support (#8847) LocalAI [bot] 2026-03-08 09:34:44 +01:00
  • d21369ad7b Update shell completion documentation URL Ettore Di Giacinto 2026-03-08 09:33:36 +01:00
  • efd402207c feat: Add shell completion support for bash, zsh, and fish (#8851) LocalAI [bot] 2026-03-08 09:32:39 +01:00
  • 6a928e70bc docs: add Table of Contents to README.md (#8846) LocalAI [bot] 2026-03-08 09:32:26 +01:00
  • 36c184175a docs: Add comprehensive API error reference documentation (#8848) LocalAI [bot] 2026-03-08 08:54:51 +01:00
  • 970079e68a fix: Remove debug print statement from soundgeneration.go (C2) (#8843) LocalAI [bot] 2026-03-08 08:49:29 +01:00
  • f347495de9 fix(qwen-tts): duplicate instruct argument in voice design mode (#8842) Weathercold 2026-03-08 03:48:22 -04:00
  • 23aa7aefed chore(docs): Populate coding guidelines in CONTRIBUTING.md (#8840) LocalAI [bot] 2026-03-08 08:20:39 +01:00
  • 1296167f84 chore: ⬆️ Update ggml-org/llama.cpp to c5a778891ba0ddbd4cbb507c823f970595b1adc2 (#8837) LocalAI [bot] 2026-03-07 23:28:06 +01:00
  • 326f4bf4bc chore(ci): drop voxcpm-cpu on aarm64 (torchcodec is not supported) Ettore Di Giacinto 2026-03-07 22:24:56 +00:00
  • 06125c338a feat: update descriptions for first 9 models in gallery/index.yaml (#8831) LocalAI [bot] 2026-03-07 12:34:29 +01:00
  • 73158600c8 chore(model gallery): 🤖 add 1 new models via gallery agent (#8830) LocalAI [bot] 2026-03-07 09:17:30 +01:00
  • 40b8f6270e chore(model gallery): 🤖 add 1 new models via gallery agent (#8828) LocalAI [bot] 2026-03-07 08:46:57 +01:00
  • ac48867b7d feat: add agentic management (#8820) Ettore Di Giacinto 2026-03-07 00:03:08 +01:00
  • e1df6807dc chore: ⬆️ Update ggml-org/llama.cpp to 566059a26b0ce8faec4ea053605719d399c64cc5 (#8822) LocalAI [bot] 2026-03-06 23:53:23 +01:00
  • ab315f2725 feat: Add LOCALAI_DISABLE_MCP environment variable to disable MCP support (#8816) LocalAI [bot] 2026-03-06 20:44:03 +01:00
  • 96efa4fce0 feat: add WebSocket mode support for the response api (#8676) BitToby 2026-03-06 12:36:59 +02:00
  • e82b861961 fix(ui): do not lock all components during load Ettore Di Giacinto 2026-03-06 09:34:54 +01:00
  • 6a15be377a chore: Add LTX-2.3 model to gallery (#8805) LocalAI [bot] 2026-03-06 09:22:31 +01:00
  • 9e1b0d0c82 fix: Add timeout-based wait for model deletion completion (#8756) LocalAI [bot] 2026-03-06 01:07:15 +01:00
  • 580517f9db feat: pass-by metadata to predict options (#8795) Ettore Di Giacinto 2026-03-05 22:50:10 +01:00
  • 0cf7c18177 chore: ⬆️ Update ggml-org/llama.cpp to a0ed91a442ea6b013bd42ebc3887a81792eaefa1 (#8797) LocalAI [bot] 2026-03-05 22:49:45 +01:00
  • ac91413eb2 chore: ⬆️ Update ggml-org/whisper.cpp to 30c5194c9691e4e9a98b3dea9f19727397d3f46e (#8796) LocalAI [bot] 2026-03-05 22:49:32 +01:00
  • 86680ff8bc fix(ui): fix /app redirect Ettore Di Giacinto 2026-03-05 21:43:43 +00:00
  • 09ddaf94b2 feat(ui): move to React for frontend (#8772) Ettore Di Giacinto 2026-03-05 21:47:12 +01:00
  • 61c139fa7d feat: Rename 'Whisper' model type to 'STT' in UI (#8785) LocalAI [bot] 2026-03-05 09:51:47 +01:00
  • 9fc77909e0 fix: Add vllm-omni backend to video generation model detection (#8659) (#8781) LocalAI [bot] 2026-03-05 01:04:47 +01:00
  • 3dce20b026 docs: add autonomous development team section to README (#8780) LocalAI [bot] 2026-03-04 23:52:36 +01:00
  • f25e450414 chore: ⬆️ Update ggml-org/llama.cpp to 24d2ee052795063afffc9732465ca1b1c65f4a28 (#8777) LocalAI [bot] 2026-03-04 23:25:48 +01:00
  • ee06892cd5 chore(model-gallery): ⬆️ update checksum (#8778) LocalAI [bot] 2026-03-04 22:02:14 +01:00
  • c25dfcc9b4 Update model and OPENAI_MODE in gallery-agent.yaml Ettore Di Giacinto 2026-03-04 18:28:53 +01:00
  • 016738a787 Remove descriptions from model entries in index.yaml Ettore Di Giacinto 2026-03-04 18:26:45 +01:00
  • 2938fe5cad chore(model gallery): 🤖 add 1 new models via gallery agent (#8770) LocalAI [bot] 2026-03-04 15:55:08 +01:00
  • 454d8adc76 feat(qwen-tts): Support using multiple voices (#8757) Andres 2026-03-04 09:47:21 +01:00
  • 6002c940a9 chore: ⬆️ Update ggml-org/llama.cpp to ecd99d6a9acbc436bad085783bcd5d0b9ae9e9e9 (#8762) LocalAI [bot] 2026-03-04 08:08:37 +01:00
  • 8e6fe4531e chore(ci): update environment variable for external backend Ettore Di Giacinto 2026-03-03 22:12:37 +01:00
  • 5203fb37a6 fix(ci): remove erroneus abspath call Ettore Di Giacinto 2026-03-03 19:07:39 +01:00
  • eb2a656575 fix: return full embedding dimensions instead of truncating trailing zeros (#8721) (#8755) LocalAI [bot] 2026-03-03 17:08:16 +01:00
  • 6e5a58ca70 feat: Add Free RPC to backend.proto for VRAM cleanup (#8751) LocalAI [bot] 2026-03-03 12:39:06 +01:00
  • 1c8db3846d chore(faster-qwen3-tts): Add anyio to requirements.txt Ettore Di Giacinto 2026-03-03 09:43:29 +01:00
  • 5139719d59 chore(model gallery): 🤖 add 1 new models via gallery agent (#8743) LocalAI [bot] 2026-03-03 09:33:11 +01:00
  • d846ad3a84 chore: ⬆️ Update ggml-org/llama.cpp to 4d828bd1ab52773ba9570cc008cf209eb4a8b2f5 (#8727) LocalAI [bot] 2026-03-02 23:22:28 +01:00
  • 50cf3ff37f chore(deps): bump github.com/google/go-containerregistry from 0.20.7 to 0.21.1 (#8736) dependabot[bot] 2026-03-02 21:44:40 +01:00
  • 74dff72551 chore(deps): bump go.opentelemetry.io/otel/metric from 1.40.0 to 1.41.0 (#8735) dependabot[bot] 2026-03-02 21:44:28 +01:00
  • c4eeab0f7c chore(deps): bump go.opentelemetry.io/otel from 1.40.0 to 1.41.0 (#8734) dependabot[bot] 2026-03-02 21:44:15 +01:00
  • 432e182af0 chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.3.0 to 1.4.0 (#8733) dependabot[bot] 2026-03-02 21:44:03 +01:00
  • d1fcd19cd3 chore(deps): bump github.com/openai/openai-go/v3 from 3.19.0 to 3.24.0 (#8732) dependabot[bot] 2026-03-02 21:43:53 +01:00
  • dc550395cb chore(deps): bump actions/upload-artifact from 6 to 7 (#8730) dependabot[bot] 2026-03-02 21:43:39 +01:00
  • 00ecc60372 chore(deps): bump actions/download-artifact from 7 to 8 (#8729) dependabot[bot] 2026-03-02 21:43:27 +01:00
  • 11443dc299 chore(model-gallery): ⬆️ update checksum (#8728) LocalAI [bot] 2026-03-02 21:43:12 +01:00
  • 6d182281cf fix: allow reranking models configured with known_usecases (#8681) LocalAI [bot] 2026-03-02 19:00:18 +01:00
  • 8f0c3cec39 chore(ci): disable CI actions Ettore Di Giacinto 2026-03-02 14:48:00 +01:00
  • 2dd4e7cdc3 fix(qwen-tts): ensure all requirements files end with newline (#8724) LocalAI [bot] 2026-03-02 13:56:11 +01:00
  • eca2c6e01c fix: Implement responsive line wrapping for model names (#8209) (#8720) LocalAI [bot] 2026-03-02 13:54:58 +01:00
  • b61536c0f4 chore: ⬆️ Update ggml-org/llama.cpp to 319146247e643695f94a558e8ae686277dd4f8da (#8707) LocalAI [bot] 2026-03-02 10:08:51 +01:00
  • 02d287a297 fix(ci): correct transformer backend path typo (#8712) LocalAI [bot] 2026-03-02 10:08:28 +01:00
  • 8b430c577b feat: Add debug logging for pocket-tts voice issue #8244 (#8715) LocalAI [bot] 2026-03-02 09:24:59 +01:00
  • 2aaddbb3b8 chore(ci): wire external backend for tests fix/ci-tests Ettore Di Giacinto 2026-03-01 21:33:20 +00:00
  • 0063e5d68f feat(swagger): update swagger (#8706) LocalAI [bot] 2026-03-01 21:33:19 +01:00
  • c7c4a20a9e fix: retry when LLM returns empty messages (#8704) Ettore Di Giacinto 2026-03-01 21:32:38 +01:00
  • 94539f3992 chore(model gallery): 🤖 add 1 new models via gallery agent (#8698) LocalAI [bot] 2026-03-01 16:54:01 +01:00
  • 525278658d chore(model gallery): 🤖 add 1 new models via gallery agent (#8696) LocalAI [bot] 2026-03-01 16:19:38 +01:00
  • 919f801e25 chore(model gallery): 🤖 add 1 new models via gallery agent (#8695) LocalAI [bot] 2026-03-01 15:58:02 +01:00
  • 362eb261c5 chore(model gallery): 🤖 add 1 new models via gallery agent (#8694) LocalAI [bot] 2026-03-01 15:40:43 +01:00
  • d407f4ead5 chore(model gallery): 🤖 add 1 new models via gallery agent (#8693) LocalAI [bot] 2026-03-01 15:25:08 +01:00
  • 1fc8ad854f fix(toolcall): consider also literal \n between tags Ettore Di Giacinto 2026-03-01 11:20:46 +01:00
  • f49a8edd87 docs: Update Home Assistant links in README.md (#8688) Loryan Strant 2026-03-01 18:28:58 +11:00
  • 510b830d2b fix: simplify CI steps, fix gallery agent (#8685) Ettore Di Giacinto 2026-03-01 01:00:30 +01:00
  • ddb36468ed chore: ⬆️ Update ggml-org/llama.cpp to 05728db18eea59de81ee3a7699739daaf015206b (#8683) LocalAI [bot] 2026-03-01 00:48:26 +01:00
  • 983db7bedc feat(ui): add model size estimation (#8684) Ettore Di Giacinto 2026-02-28 23:03:47 +01:00
  • b260378694 docs: add TLS reverse proxy configuration guide (#8673) LocalAI [bot] 2026-02-28 23:02:17 +01:00
  • b10443ab5a feat(models): add model storage size display and RAM warning (#8675) LocalAI [bot] 2026-02-28 22:05:01 +01:00
  • b647b6caf1 fix: properly sync model selection dropdown in video generation UI (#8680) LocalAI [bot] 2026-02-28 13:11:33 +01:00
  • c187b160e7 fix(gallery): clean up partially downloaded backend on installation failure (#8679) LocalAI [bot] 2026-02-28 13:10:53 +01:00
  • 42e580bed0 fix: whisper breaking on cuda-13 (use absolute path for CUDA directory detection) (#8678) LocalAI [bot] 2026-02-28 09:10:40 +01:00
  • 5e13193d84 docs: add CDI driver config for NVIDIA GPU in containers (fix #8108) (#8677) LocalAI [bot] 2026-02-28 08:42:53 +01:00
  • 1c5dc83232 chore(deps): bump llama.cpp to 'ecbcb7ea9d3303097519723b264a8b5f1e977028' (#8672) Ettore Di Giacinto 2026-02-28 00:33:56 +01:00
  • 73b997686a chore: ⬆️ Update ggml-org/whisper.cpp to 9453b4b9be9b73adfc35051083f37cefa039acee (#8671) LocalAI [bot] 2026-02-27 22:28:48 +01:00
  • 00abf1be1f fix(qwen3.5): add qwen3.5 preset and mimick llama.cpp's PEG (#8668) Ettore Di Giacinto 2026-02-27 12:15:00 +01:00
  • 959458f0db fix(gallery): add fallback URI resolution for backend installation (#8663) LocalAI [bot] 2026-02-27 10:56:33 +01:00
  • dfc6efb88d feat(backends): add faster-qwen3-tts (#8664) LocalAI [bot] 2026-02-27 08:16:51 +01:00
  • e169492543 fix: this backend is CUDA only faster-qwen3-tts Ettore Di Giacinto 2026-02-26 23:08:24 +00:00
  • 51c26f1f39 feat(backends): add faster-qwen3-tts Ettore Di Giacinto 2026-02-26 22:59:10 +00:00
  • 65082b3a6f fix: Add named volumes for Windows Docker compatibility (#8661) LocalAI [bot] 2026-02-26 23:18:53 +01:00
  • 0483d47674 Change condition for dependabot job in workflow Ettore Di Giacinto 2026-02-26 23:17:33 +01:00
  • 8ad40091a6 chore: ⬆️ Update ggml-org/llama.cpp to 723c71064da0908c19683f8c344715fbf6d986fd (#8660) LocalAI [bot] 2026-02-26 22:34:47 +01:00
  • 8bfe458fbc fix: change file permissions from 0600 to 0644 in InstallModel (#8657) LocalAI [bot] 2026-02-26 09:38:54 +01:00
  • 657ba8cdad fix(chat): do not send thinking/reasoning messages to the LLM (#8656) Ettore Di Giacinto 2026-02-26 00:06:35 +01:00
  • fb86f6461d chore: ⬆️ Update ggml-org/llama.cpp to 3769fe6eb70b0a0fbb30b80917f1caae68c902f7 (#8655) LocalAI [bot] 2026-02-26 00:05:03 +01:00
  • 1027c487a6 fix: reload model after editing YAML config (issue #8647) (#8652) LocalAI [bot] 2026-02-25 22:18:42 +01:00
  • bb226d1eaa feat(swagger): update swagger (#8654) LocalAI [bot] 2026-02-25 21:52:35 +01:00
  • b032cf489b fix(chatterbox): add support for cuda13/aarch64 (#8653) Ettore Di Giacinto 2026-02-25 21:51:44 +01:00
  • 3ac7301f31 Add sample_rate support to TTS API via post-processing resampling (#8650) Copilot 2026-02-25 16:36:27 +01:00
  • c4783a0a05 chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/vllm (#8635) dependabot[bot] 2026-02-25 08:17:32 +01:00
  • c44f03b882 chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/rerankers (#8636) dependabot[bot] 2026-02-25 08:16:57 +01:00