THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-q97c-p368-75c4 (medium) — vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

[GHSA] GHSA-q97c-p368-75c4 (medium) — vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

medgithub_advisoriesPublished 2026-10-28

GHSA-q97c-p368-75c4 Severity: medium CVE: CVE-2026-115916

vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

For a model whose vocabulary size is an exact multiple of the embedding padding size (64) — e.g. any Llama-2-family model, vocab 32000 — a single request carrying a pre-tokenized prompt with token id equal to the voc

Indicators of compromise

Original source: https://github.com/advisories/GHSA-q97c-p368-75c4