Event ·Multi-source

vLLM v0.33.0 发布:新增 4 个模型支持与 GB300 解码优化

vLLM v0.33.0 共包含 927 次提交,由 389 位贡献者完成,其中 122 位是首次参与。新版本加入 Reflection Beam-1.0、Step-5 Preview、Nemotron Parse 3.5、MiniCPM-OCR 1.0 四个模型的支持。推理引擎升级到 PyTorch 2.14,提供 CUDA 13.0 专用 wheel 包。投机解码方面新增 XPress refiner 与 FLy lossy verify(1.04–1.31 倍加速),DSpark 在 GB300 上从 1373 提升到 3390 tok/s。NVIDIA 解码路径实现 1.5–2 倍延迟降低,TTFT 下降 39–48%,同时 ROCm 10.0 成为默认配置。

Current read

vLLM 又发新版了,这版支持 Step-5 Preview 等 4 个新模型,GB300 上解码快了最多 2 倍,自建推理服务的可以升级看看。

11 sources71° AI heatLast updated 2026/11/3 23:53:16

Evidence

11 sources
Related source 2marktechpost
View source
Related source 3Artificial Analysis
View source
Related source 5LlamaIndex
View source
Related source 7Fireworks AI
View source
Related source 8arXiv cs.AI
View source
Related source 9Tech in Asia
View source
Related source 10Gorden Sun
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

vLLM v0.33.0 Ships PyTorch 2.14, New Models and NVIDIA Gains · 事件专题 | AITOP