{"id":"ghsa-ghsa-q97c-p368-75c4","seq":2056929,"kind":"advisory","title":"vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)","url":"https://github.com/advisories/GHSA-q97c-p368-75c4","permalink":"https://vulnpulse.app/items/ghsa-ghsa-q97c-p368-75c4","summary":"影響: pip:vllm < 0.32.0 → 0.32.0\nFor 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 vocab size (32000) passes vLLM's input-id validation but is one past the last embedding row. At tensor-parallel size 1 the embedding lookup does not mask indices, so the id reaches F.embedding out of range and raises a CUDA device-side assert, which poisons the engine's CUDA context an…","severity":"medium","techs":["python"],"cves":["CVE-2026-115916"],"tags":["GHSA-q97c-p368-75c4","vllm"],"source":{"id":"ghsa","name":"GitHub Advisory Database"},"published_at":"2026-10-28T21:15:08.000Z","fetched_at":"2026-10-29T00:48:52.653Z"}