What's new in 1.11.0 (2025-10-19)
These are the changes in inference v1.11.0.
New features
- FEAT: [model]Support Qwen3-4B Instruct/Thinking by @Jun-Howie in #4129
- FEAT: OpenAI image edit api support by @OliverBryant in #4110
- FEAT: Add vllm multi model support by @zhcn000000 in #4126
Enhancements
- ENH: Add support for vllm awq 8bit and support qwen3-vl 30b by @zhcn000000 in #4122
- BLD: Fix CI run failed issue by @OliverBryant in #4103
- BLD: fix cu128 Dockerfile by @zwt-1234 in #4145
Bug fixes
- BUG: [UI] launch button stays disabled when n_gpu_layers=-1. by @yiboyasss in #4127
- BUG: vllm structured output issue by @OliverBryant in #4142
Documentation
Others
- BLD：Docker.cu128 Upgrade VLLM to 0.10.2 by @zwt-1234 in #4134
- FEAT：[model] support MiniCPM-V-4.5 by @OliverBryant in #4136
- chore: sync models JSON [audio, image, llm, video] by @XprobeBot in #4135
- chore: sync models JSON [llm] by @XprobeBot in #4140
New Contributors
- @XprobeBot made their first contribution in #4135
Full Changelog: v1.10.1...v1.11.0