What's new in 1.13.0 (2025-11-15)
These are the changes in inference v1.13.0.
New features
- FEAT: [model] Qwen3-VL-MLX support by @OliverBryant in #4203
- FEAT: auto batch embedding by @qinxuye in #4197
- FEAT: update models via Xinference model hub by @OliverBryant in #4241
Enhancements
- ENH: IndexTTS2 stream output by @OliverBryant in #4213
- ENH: IndexTTS2 offline deploy by @OliverBryant in #4202
- ENH: add embedding benchmark by @llyycchhee in #4244
- BLD: Fix CI error caused by peft version by @OliverBryant in #4249
Bug fixes
- BUG: Deepseek-OCR error in docker by @OliverBryant in #4208
- BUG: ensure unique tool call IDs using UUID by @amumu96 in #4242
- BUG: Fix cache model not shown on audio、video and image by @OliverBryant in #4247
Documentation
- DOC: added new models by @qinxuye in #4206
- DOC: Xinference 1.12.0 installation issues with uv by @qiulang in #4228
- DOC: add model update documentation. by @yiboyasss in #4246
Others
- chore: sync models JSON [audio, embedding, image, llm, rerank, video] by @XprobeBot in #4214
- chore: sync models JSON [audio, embedding, image, llm, rerank, video] by @XprobeBot in #4226
- chore: sync models JSON [audio] by @XprobeBot in #4243
Full Changelog: v1.12.0...v1.13.0