v0.20.0

v0.20.0 vllm-project / vllm Public Uh oh! There was an error while loading.

This PolicyChange is relevant to the technology intelligence record because it involves DeepSeek, OpenAI, Mistral AI, 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 v0.20.0 khluu released this 27 Apr 21:20 · 5903 commits to main since this release v0.20.0 88d34c6 vLLM v0.20.0 Highlights This release features 752 commits from 320 contributors (123 new)!
• DeepSeek V4 : Initial DeepSeek V4 support landed ( #40860 ), with DSML token-leakage fix in DSV4/3.2 ( #40806 ), DSA + MTP IMA fix ( #40772 ), and a silu clamp limit on the shared expert ( #40950 ).
• CUDA 13.0 default : Default CUDA wheel on PyPI and vllm/vllm-openai:v0.20.0 image switched to CUDA 13.0; architecture lists and build-args cleaned up ( #39878 ), and CUDA bumped to 13.0.2 to match PyTorch 2.11.0 ( #40669 ).
• As a general rule of thumb, our CUDA version policy follows PyTorch's.