Public mode

No access to your tenant or devices. Every item links to its source. What this means

Sources need attention Customize Public modeDiscuss ChangeIntel on Discord

vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs

CVSS 4.0 6.3 MEDIUMCVSS 3.1 3.7 LOWCheck source for fixed versionsKEV status unknown

Historical advisory recorded 23 Oct 2026 15:48:27 UTC. Read the latest advisory.

cve-program · CVE-2026-93841

Published

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.

Read the publisher's advisory

Affected versions, risk and source history

cve-program · CVE-2026-93841

Published

vllm

Vendor product

Publisher's version information

Shown as published. These rules are not interpreted as NuGet package version ranges.

{
                    "vendor": "vllm-project",
                    "product": "vllm",
                    "defaultStatus": "unaffected",
                    "packageURL": "pkg:pypi/vllm",
                    "versions": [
                        {
                            "version": "0",
                            "status": "affected",
                            "versionType": "semver",
                            "lessThanOrEqual": "0.29.0"
                        }
                    ]
                }

Original source record · Cite this exact observation · Complete original publisher JSON

ChangeIntel

An IT change radar: releases, security, known issues, retirements, documentation changes, and service status from public sources. Every item links to supporting evidence; dates and statuses can change after they are read.

Sources read 16 Nov 10:01 UTC · 274 of 275 readable · 252 fully read · 18 waiting for GitHub's hourly limit · documentation 469/469 current