| Component | vLLM |
| Severity | medium (CVSS 6.5) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| Published (NVD) | 2026-10-26 |
| Affected versions | < 0.32.0 from the CVE Program record written by the CNA that assigned the CVE |
| Fixed in | 0.32.0 |
| Weakness | CWE-129CWE-193 |
| CISA KEV | not listed |
NVD description
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.
What to do
- Upgrade vLLM to
0.32.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-115916
- https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229
- https://github.com/vllm-project/vllm/pull/59491
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4