Advisory

PYSEC-2026-4347

Also known as: CVE-2026-115916, GHSA-q97c-p368-75c4

Summary

The record has no summary.

Details

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.

Severity

Medium Basis: CVSS v3 score 6.5, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Dates

Published
2026-10-26 18:17 UTC
Modified
2026-10-29 11:00 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0, fixed 0.32.0 (ecosystem)

Fixed versions

0.32.0

Fix

  • Fixed version 0.32.0
    pip install --upgrade vllm==0.32.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences