v0.22.0

v0.22.0 vllm-project / vllm Public Uh oh! There was an error while loading.

This HardwareLaunch is relevant to the technology intelligence record because it involves DeepSeek, Cohere, Meta, NVIDIA. The source article should remain the factual reference for follow-up coverage.

• vllm-project / vllm Public Uh oh!
• There was an error while loading.
• Notifications You must be signed in to change notification settings Fork 22.7k Star 92.7k v0.22.0 khluu released this 29 May 10:28 · 5067 commits to main since this release v0.22.0 0b3ba88 Highlights This release features 459 commits from 230 contributors (63 new)!
• DeepSeek V4 maturity : DeepSeek V4 received a major hardening pass this cycle — the model was reorganized into a dedicated vllm/models/deepseek_v4/ package ( #43004 , #43039 , #43073 , #43077 , #43149 ), gained NVFP4 fused MoE support ( #42209 ), full + piecewise CUDA graph ( #42604 ), and MTP speculative decoding ( #43385 ).
• A large set of fused kernels (MegaMoE, mhc , Q-norm, indexer, sparse MLA) and ROCm parity fixes landed alongside accuracy fixes ( #42810 , #43710 ).
• Model Runner V2 advances toward default : MRv2 is now default for Qwen3 dense models.