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…

Read on GitHub Advisory Database

On 10/29/2026, 06:15 AM, GitHub Advisory Database published "vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)" (type: Advisory). Severity is "Medium" (medium). Related technologies: Python. CVE: CVE-2026-115916.