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

影響: pip:vllm < 0.32.0 → 0.32.0

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 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…

GitHub Advisory Database에서 읽기

2026. 10. 29. 오전 06:15, GitHub Advisory Database에서 "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)"을(를) 게시했습니다 (유형: 취약점 권고). 심각도는 "보통"(medium)입니다. 관련 기술: Python. CVE: CVE-2026-115916.