CVE-2026-115916 — 脆弱性インテリジェンス
vllm — vllm
公表日:
- CVSS
- 6.5
- CISA KEV
- 未掲載（悪用がないことを意味しません）
情報源の原文（翻訳ではありません）
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.