v3.10.1
v3.10.1
Fixes
- Reasoning detection now works on reasoning/instruct models without explicit thinking tags
- Runtime tracing can be enabled on first request (trace buffer initialization fix)
- LTX-2 video generation: fixed API calls and added GGUF support
Features
- OpenResponses now supports reasoning blocks
- Automatic thinking/reasoning capability detection from backend (no manual config needed)
- Qwen-TTS backend support
Dependencies
- cogito 0.7.2 → 0.8.1
- Updated llama.cpp, stable-diffusion.cpp, whisper.cpp to latest commits
This is a small patch release intended to provide bugfixes and minor polishment, along, we also added support to Qwen-TTS that was just released yesterday.
- Fix reasoning detection on reasoning and instruct models
- Support reasoning blocks with openresponses
- API fixes to correctly run LTX-2
- Support Qwen3-TTS!
What's Changed
Bug fixes :bug:
- fix(reasoning): support models with reasoning without starting thinking tag by @mudler in https://github.com/mudler/LocalAI/pull/8132
- fix(tracing): Create trace buffer on first request to enable tracing at runtime by @richiejp in https://github.com/mudler/LocalAI/pull/8148
- fix(videogen): drop incomplete endpoint, add GGUF support for LTX-2 by @mudler in https://github.com/mudler/LocalAI/pull/8160
Exciting New Features 🎉
- feat(openresponses): Support reasoning blocks by @mudler in https://github.com/mudler/LocalAI/pull/8133
- feat: detect thinking support from backend automatically if not explicitly set by @mudler in https://github.com/mudler/LocalAI/pull/8167
- feat(qwen-tts): add Qwen-tts backend by @mudler in https://github.com/mudler/LocalAI/pull/8163
🧠 Models
- chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8128
- chore(model gallery): add flux 2 and flux 2 klein by @mudler in https://github.com/mudler/LocalAI/pull/8141
- chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/8153
- chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8157
- chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8170
👒 Dependencies
- chore(deps): bump github.com/mudler/cogito from 0.7.2 to 0.8.1 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8124
Other Changes
- feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/8098
- chore: :arrow_up: Update ggml-org/llama.cpp to
287a33017b32600bfc0e81feeb0ad6e81e0dd484by @localai-bot in https://github.com/mudler/LocalAI/pull/8100 - chore: :arrow_up: Update leejet/stable-diffusion.cpp to
2efd19978dd4164e387bf226025c9666b6ef35e2by @localai-bot in https://github.com/mudler/LocalAI/pull/8099 - docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/8120
- chore: :arrow_up: Update leejet/stable-diffusion.cpp to
a48b4a3ade9972faf0adcad47e51c6fc03f0e46dby @localai-bot in https://github.com/mudler/LocalAI/pull/8121 - chore: :arrow_up: Update ggml-org/llama.cpp to
959ecf7f234dc0bc0cd6829b25cb0ee1481aa78aby @localai-bot in https://github.com/mudler/LocalAI/pull/8122 - chore(deps): Bump llama.cpp to '1c7cf94b22a9dc6b1d32422f72a627787a4783a3' by @mudler in https://github.com/mudler/LocalAI/pull/8136
- chore: drop noisy logs by @mudler in https://github.com/mudler/LocalAI/pull/8142
- chore: :arrow_up: Update ggml-org/llama.cpp to
ad8d85bd94cc86e89d23407bdebf98f2e6510c61by @localai-bot in https://github.com/mudler/LocalAI/pull/8145 - chore: :arrow_up: Update ggml-org/whisper.cpp to
7aa8818647303b567c3a21fe4220b2681988e220by @localai-bot in https://github.com/mudler/LocalAI/pull/8146 - feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/8150
- chore(diffusers): add 'av' to requirements.txt by @mudler in https://github.com/mudler/LocalAI/pull/8155
- chore: :arrow_up: Update leejet/stable-diffusion.cpp to
329571131d62d64a4f49e1acbef49ae02544fdcdby @localai-bot in https://github.com/mudler/LocalAI/pull/8152 - chore: :arrow_up: Update ggml-org/llama.cpp to
c301172f660a1fe0b42023da990bf7385d69adb4by @localai-bot in https://github.com/mudler/LocalAI/pull/8151 - chore: :arrow_up: Update ggml-org/llama.cpp to
a5eaa1d6a3732bc0f460b02b61c95680bba5a012by @localai-bot in https://github.com/mudler/LocalAI/pull/8165 - chore: :arrow_up: Update leejet/stable-diffusion.cpp to
5e4579c11d0678f9765463582d024e58270faa9cby @localai-bot in https://github.com/mudler/LocalAI/pull/8166
Full Changelog: https://github.com/mudler/LocalAI/compare/v3.10.0...v3.10.1