Not a U.S. government website. NDD is an independent vulnerability database by Volerion and is not affiliated with or endorsed by NIST or NVD.
VOLERION
Volerion Security Research

NOT DEFERRED DATABASE

VULNERABILITIES

CVE-2026-115916 Details

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.

Metrics

CVSS 3.x Severity and Vector Strings:

CNA: [email protected]CVSS-B:6.5 MEDIUMVector:CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References to Advisories, Solutions, and Tools

By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.

URLSource(s)Tag(s)
https://github.com/vllm-project/vllm/commit/37cecc8141e2dcba9dd534897a164d4baaf27229 [email protected]Patch
https://github.com/vllm-project/vllm/pull/59491 [email protected]Patch
https://github.com/vllm-project/vllm/releases/tag/v0.32.0 [email protected]Release Notes
https://github.com/vllm-project/vllm/security/advisories/GHSA-q97c-p368-75c4 [email protected]PatchVendor Advisory

Weakness Enumeration

CWE-IDCWE NameSource
CWE-129Improper Validation of Array Index[email protected]
CWE-193Off-by-one Error[email protected]

Affected Products

ProductVersions
vllm vllm
< 0.32.0

CPE

  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

Remediation

  • No remediation found in references.

Change History

3 change records found show changes

QUICK INFO

CVE Dictionary Entry:
CVE-2026-115916
NVD Published Date:
Oct 26, 2026
NVD Last Modified:
Nov 2, 2026
Source:
[email protected]
CVE-2026-115916 Details - Not Deferred