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.
Fix
Patch, vendor advisory and mitigation references on NVD 3
- https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229 Patch
- https://github.com/vllm-project/vllm/pull/59491 Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4 Patch, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 6
- Cpes+1 CPE criteria (now 1)NVD modified 2026-10-28 15:36
- StatusPublished → AnalyzedNVD modified 2026-10-28 15:36
- StatusAwaiting Analysis → PublishedNVD modified 2026-10-26 17:18
- StatusPublished → Awaiting AnalysisNVD modified 2026-10-26 18:34
- StatusReceived → PublishedNVD modified 2026-10-26 17:18
- First seenCVSS 6.5NVD modified 2026-10-26 18:17
Affected (CPE criteria) 1
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References 4
- https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229 Patch
- https://github.com/vllm-project/vllm/pull/59491 Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4 Patch, Vendor Advisory