---
id: CVE-2026-93841
title: >-
  vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton
  _bincount_kernel where prompt token IDs index the penalty prompt-presence
  bitset without bounds checking against vocabulary size
summary: >-
  vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton
  _bincount_kernel where prompt token IDs index the penalty prompt-presence
  bitset without bounds checking against vocabulary size. Attackers can submit
  multimoda…
severity: low
cvss: 3.7
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N'
cwe:
  - CWE-129
  - CWE-787
vendor: vllm-project
product: vllm
affected:
  - vllm <= 0.29.0
published: '2026-09-18'
updated: '2026-09-22'
sourceUpdated: '2026-09-22T20:25:55.870'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-93841'
references:
  - url: 'https://github.com/vllm-project/vllm'
    label: disclosure@vulncheck.com
  - url: >-
      https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255
    label: disclosure@vulncheck.com
  - url: >-
      https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37
    label: disclosure@vulncheck.com
  - url: 'https://github.com/vllm-project/vllm/pull/49081'
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampler-state-corruption-via-unvalidated-prompt-token-ids
    label: disclosure@vulncheck.com
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-93841.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-93841'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2539027'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-93841'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-93841'
tags:
  - nvd
  - cve.org
  - csaf
  - vex
  - red-hat
epss: 0.00393
epssPercentile: 0.30594
ssvc:
  exploitation: none
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-09-21T16:22:54.286847Z'
ingestedAt: '2026-09-18T19:49:30.603Z'
---

## Overview

vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.

## Vendor advisories

- **Red Hat VEX** · Low · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-09-24 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-93841.json)