What's new in 1.12.0 (2025-11-02)
These are the changes in inference v1.12.0.
New features
- FEAT: [model] support jina-reranker-v3 by @llyycchhee in #4156
- FEAT: [model] qwen3-omni by @qinxuye in #4137
- FEAT: xinference python 3.13 support by @OliverBryant in #4164
- FEAT: add OCR gradio UI by @OliverBryant in #4185
- FEAT: [model] DeepSeek-OCR by @OliverBryant in #4187
Enhancements
- ENH: adding lightning support for qwen-image-edit-2509 by @qinxuye in #4151
- BLD: torchaudio 2.9 introduces the breaking change in torchaudio.save by @qiulang in #4178
- BLD: fix setup.cfg for python 3.12 and fix dockerfile by @zwt-1234 in #4192
- BLD: fix Dockerfile.cpu by @zwt-1234 in #4195
- REF: Modified the batch lock logic by @OliverBryant in #4162
- BLD: fix transformers version in cu128 dockerfile by @zwt-1234 in #4152
Bug fixes
- BUG: repair qwen3 model transformers random characters by @OliverBryant in #4148
- BUG: [UI] resolve progress bar display issue. by @yiboyasss in #4150
- BUG: fix IndexTTS2 on transformes 4.57.1 by @OliverBryant in #4158
- BUG: fix error when xinference run on docker with oath2 by @OliverBryant in #4161
- BUG: fix qwen3-vl launch error by @amumu96 in #4190
Documentation
- DOC: add release notes doc by @qinxuye in #4157
- DOC: Add PyPI mirror configuration guide for audio package installation by @qiulang in #4177
Others
- chore: sync models JSON [image, llm] by @XprobeBot in #4149
- chore: sync models JSON [rerank] by @XprobeBot in #4159
- chore: sync models JSON [llm] by @XprobeBot in #4160
- chore: sync models JSON [llm] by @XprobeBot in #4171
- chore: sync models JSON [image] by @XprobeBot in #4186
- chore: sync models JSON [embedding, image] by @XprobeBot in #4188
- chore: sync models JSON [llm] by @XprobeBot in #4191
Full Changelog: v1.11.0...v1.12.0