vLLM v0.31.0 adds DeepSeek-V4.1-Flash support and new serving features

vLLM v0.31.0 is released with 717 commits from 307 contributors, including 96 first-time contributors.

Highlights include DeepSeek-V4.1-Flash support, a vllm preload command that keeps weights in GPU memory across restarts, and Model Runner V2 with draft-model speculative decoding.

The release also adds large-scale serving, scheduling, and HiSparse fixes, with full notes linked on GitHub.