ai_security▌

← feed

NOTABLE

vLLM advisory: cross-user token data leakage under async scheduling plus pipeline parallelism

With the V1 model runner using async scheduling together with pipeline_parallel_size > 1, token data from a previous user's request context can leak into another user's response. The repo security advisory (medium, published Nov 9 17:29 UTC) covers vLLM v0.16.0 through v0.20.2, fixed in v0.21.0, with the technical analysis in vllm issue 38903. First ingestion: absent from items.json and from every earlier sweep log.

released 2026-11-09 · ingested 2026-11-11T02:40Z

Sources

Primary source

Cite this

APA

AI Security Index. (2026). vLLM advisory: cross-user token data leakage under async scheduling plus pipeline parallelism. AI Security Index. https://github.com/vllm-project/vllm/security/advisories/GHSA-v97p-wpxp-px84

BibTeX

@misc{aisec-2026-11-09-vllm-cross-user-token-leak-async-pipeline-parallel,
  title  = {vLLM advisory: cross-user token data leakage under async scheduling plus pipeline parallelism},
  year   = {2026},
  howpublished = {\url{https://github.com/vllm-project/vllm/security/advisories/GHSA-v97p-wpxp-px84}},
  note   = {AI Security Index item 2026-11-09-vllm-cross-user-token-leak-async-pipeline-parallel}
}