Vulnerability 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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | < 0.32.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf2Patch
- https://github.com/vllm-project/vllm/pull/59491Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4PatchVendor Advisory
FAQ
What is CVE-2026-115916?
CVE-2026-115916 is a vulnerability with a CVSS score of 6.5 (MEDIUM). 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...
How severe is CVE-2026-115916?
CVE-2026-115916 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-115916?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.