vLLM 0.31.0 released with a preload command for faster engine restarts

On October 5, 2026 the vLLM project published version 0.31.0 on GitHub. The release notes highlight a new vllm preload command that launches a weight-cache daemon to keep post-quantized weights in GPU memory across engine restarts, and experimental engine snapshots (vllm snapshot create/restore) that use CRIU to restore a fully initialized TP1 engine. Under security, the notes say per-request mm_processor_kwargs and media_io_kwargs are now rejected unless --trust-request-mm-kwargs is set. The release also lists breaking changes, including the removal of tokenizer_mode="slow", and performance work for DeepSeek-V4.1-Flash. USASI has not tested any of these changes.1

USASI. (2026, October 6). vLLM 0.31.0 released with a preload command for faster engine restarts. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/vllm-0-31-0-released/

@misc{usasi_news_vllm_0_31_0_released,
  author = {{USASI}},
  title = {vLLM 0.31.0 released with a preload command for faster engine restarts},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/vllm-0-31-0-released/}},
  note = {United States of America Superintelligence. Last updated 2026-10-06}
}