vLLM releases v0.33.0 with new model support and drops CUDA 12.9 buildsMachine translation
vLLM 发布 v0.33.0，新增模型支持并停止提供 CUDA 12.9 构建
vLLM v0.33.0 adds support for models including Reflection Beam-1.0 and Step-5 Preview, and upgrades to PyTorch 2.14.0. Release wheels and images are now CUDA 13.0 only, so teams using CUDA 12.9 builds need to switch to the default CUDA 13.0 artifacts.
The complete source text is not yet available.
Read at the original source