Starstruk Logo MarkStarstruk

v1.13.0

xorbitsai/inferencev1.13.0Nov 15, 2025by XprobeBot

AI Summary

This release adds Qwen3-VL-MLX support, introduces auto batch embedding, updates models via Xinference model hub, and enhances IndexTTS2 capabilities.

Key Highlights

  • Support Qwen3-VL-MLX
  • Auto batch embedding
  • Update models via Xinference model hub
  • IndexTTS2 stream output
  • IndexTTS2 offline deploy

New Features

  • Support Qwen3-VL-MLX
  • Auto batch embedding
  • Update models via Xinference model hub

Full Release Notes

# 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 https://github.com/xorbitsai/inference/pull/4203
* FEAT: auto batch embedding by @qinxuye in https://github.com/xorbitsai/inference/pull/4197
* FEAT: update models via Xinference model hub by @OliverBryant in https://github.com/xorbitsai/inference/pull/4241
## Enhancements
* ENH: IndexTTS2 stream output by @OliverBryant in https://github.com/xorbitsai/inference/pull/4213
* ENH: IndexTTS2 offline deploy by @OliverBryant in https://github.com/xorbitsai/inference/pull/4202
* ENH: add embedding benchmark by @llyycchhee in https://github.com/xorbitsai/inference/pull/4244
* BLD: Fix CI error caused by peft version by @OliverBryant in https://github.com/xorbitsai/inference/pull/4249
## Bug fixes
* BUG: Deepseek-OCR error in docker by @OliverBryant in https://github.com/xorbitsai/inference/pull/4208
* BUG: ensure unique tool call IDs using UUID by @amumu96 in https://github.com/xorbitsai/inference/pull/4242
* BUG: Fix cache model not shown on audio、video and image by @OliverBryant in https://github.com/xorbitsai/inference/pull/4247
## Documentation
* DOC: added new models by @qinxuye in https://github.com/xorbitsai/inference/pull/4206
* DOC: Xinference 1.12.0 installation issues with uv by @qiulang in https://github.com/xorbitsai/inference/pull/4228
* DOC: add model update documentation. by @yiboyasss in https://github.com/xorbitsai/inference/pull/4246
## Others
* chore: sync models JSON [audio, embedding, image, llm, rerank, video] by @XprobeBot in https://github.com/xorbitsai/inference/pull/4214
* chore: sync models JSON [audio, embedding, image, llm, rerank, video] by @XprobeBot in https://github.com/xorbitsai/inference/pull/4226
* chore: sync models JSON [audio] by @XprobeBot in https://github.com/xorbitsai/inference/pull/4243


**Full Changelog**: https://github.com/xorbitsai/inference/compare/v1.12.0...v1.13.0