What's new in 1.10.1 (2025-10-01)
These are the changes in inference v1.10.1.
New features
- FEAT: Openai API support sglang json structured output by @OliverBryant in #4070
- FEAT: [UI] support request_limits parameter for all models. by @yiboyasss in #4081
- FEAT: support list flexible model via webui and cmdline by @leslie2046 in #4085
- FEAT: [model] Support IndexTTS2 by @OliverBryant in #4078
- FEAT: [UI] support dynamic download_hub detection. by @yiboyasss in #4082
- FEAT: [model] qwen-image-edit-2509 by @qinxuye in #4099
- FEAT: [model] baichuan-M2 by @Jun-Howie in #4107
- FEAT: [model] Support Qwen3-VL by @Jun-Howie in #4112
- FEAT: [model] Support Qwen3-Next by @Jun-Howie in #4113
Enhancements
- ENH: optimize MPS on Mac for Qwen2.5-VL by @SolardiaX in #3524
- ENH: deepseek-r1-0528 support tool_calls by @amumu96 in #4106
- BLD: update funasr by @leslie2046 in #4062
- BLD: Update Dockerfile.cu128 by @zwt-1234 in #4114
- REF: [UI] refactor the launch model page. by @yiboyasss in #3940
Bug fixes
- BUG: Optimize rerank model lookup logic and add support for video model type by @amumu96 in #4063
- BUG: Fix seed-oss required VLLM_VERSION by @Jun-Howie in #4071
- BUG: fix register_model when model name is duplicated by @llyycchhee in #4076
- BUG: [UI] fix the custom model drawer component could not be opened. by @yiboyasss in #4089
- BUG: Fix the issue where registered models cannot use tools by @amumu96 in #4100
- BUG: fix finish_reason field handling logic by @amumu96 in #4105
- BUG: vllm structured output compatibility by @OliverBryant in #4111
Documentation
New Contributors
- @chixq made their first contribution in #3771
- @SolardiaX made their first contribution in #3524
Full Changelog: v1.10.0...v1.10.1