Bug 2539027 (CVE-2026-93841)

Summary: CVE-2026-93841 vllm: vLLM: Memory corruption via unvalidated prompt token IDs
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security DevOps Team <prodsec-dev>
Status: NEW --- QA Contact:
Severity: low Docs Contact:
Priority: low    
Version: unspecifiedCC: alinfoot, bbrownin, dtrifiro, weaton
Target Milestone: ---Keywords: Security
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc Text:
A flaw was found in vLLM. This memory corruption vulnerability exists in the Triton _bincount_kernel, where prompt token identifiers (IDs) are used to index a bitset without proper bounds checking against the vocabulary size. A remote attacker can exploit this by submitting multimodal audio requests containing tokens equal to the vocabulary size. This leads to out-of-bounds writes, which can corrupt the sampler state of concurrent requests and alter repetition penalty behavior.
 Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-09-22 21:59:37 UTC 
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.