UpHeron
All vulnerabilities

Servers and applications

CVE-2026-115916

Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

Severity
Medium 6.5
Published
20 Oct 2026
Last changed
2 Nov 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.32.0
Also known as
GHSA-q97c-p368-75c4
Sources
NVD, CVE Program, Project advisories (GitHub)

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…

Affected software

SoftwareAffected versions
vLLMServers and applications · cna:vllm-project|vllm
  • Every version before 0.32.0
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.32.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.32.0

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-115916
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-115916
  • GitHub Advisory Database https://github.com/advisories/GHSA-q97c-p368-75c4
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4