vLLM 0.32.0 released with a structured decisions endpoint and wider low-precision KV cache support

On October 18, 2026 the vLLM project published version 0.32.0 on GitHub. The release notes highlight a new POST /v1/systemone endpoint that answers choice, noul and score questions over a structured state, and a new hf tool and reasoning parser that reads a checkpoint's response_template so models that ship it need no model-specific parser. The notes also describe NVFP4 KV cache support on more GPU architectures and new model support, including EmbeddingGemma 2, MiniCPM-V 4.7 and Nemotron 3.5 ASR. Under security, they list fixes for three advisories and say CORS no longer allows every origin by default; breaking changes include dropping Python 3.10 and removing cascade attention. USASI has not tested any of these changes.1

USASI. (2026, October 19). vLLM 0.32.0 released with a structured decisions endpoint and wider low-precision KV cache support. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/vllm-0-32-0-released/

@misc{usasi_news_vllm_0_32_0_released,
  author = {{USASI}},
  title = {vLLM 0.32.0 released with a structured decisions endpoint and wider low-precision KV cache support},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/vllm-0-32-0-released/}},
  note = {United States of America Superintelligence. Last updated 2026-10-19}
}