Skip to main content

CVE-2026-94626: Memory Allocation with Excessive Size Value in vllm-project vllm

0
High
VulnerabilityCVE-2026-94626cvecve-2026-94626
Published: 09/21/2026 (09/21/2026, 22:04:15 UTC)
Source: CVE Database V5
Vendor/Project: vllm-project
Product: vllm

Description

vLLM versions up to 0.29.0 contain a vulnerability where the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints is not validated. This allows attackers to request memory allocations of arbitrary size, potentially exhausting system memory and causing the decode worker process to be terminated by the kernel's out-of-memory (OOM) killer.

CVSS v4.0

Score 8.7high

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
None
Vuln. Integrity
None
Vuln. Availability
High
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Affected software

vllm-project

vllm

Affected versions
>=0 <=0.29.0
GitHub Actionsmore threats →ai
vllm-project/vllm
pkg:github/vllm-project/vllm
Affected versions
>=0 <0.29.1

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/21/2026, 22:31:32 UTC

Technical Analysis

CVE-2026-94626 is a memory allocation vulnerability in vLLM through version 0.29.0. The software fails to validate the tp_size parameter in the kv_transfer_params function used on OpenAI-compatible completion endpoints. Attackers can supply excessively large tp_size values in prefill/decode disaggregated deployments, leading to unbounded memory allocation requests. This can exhaust available memory resources and trigger the kernel's OOM-killer to terminate the decode worker process, resulting in denial of service.

Potential Impact

Successful exploitation allows an unauthenticated attacker to cause a denial of service by exhausting system memory, leading to the termination of the decode worker process. This disrupts normal operation of the vLLM service but does not indicate direct code execution or data compromise based on the provided information.

Mitigation Recommendations

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict access to the vulnerable endpoints to trusted users and monitor resource usage to detect abnormal memory consumption patterns.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-09-21T21:42:28.781Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6ab1acdf55bf5e2cf58d35c4

Added to database: 09/21/2026, 22:17:03 UTC

Last enriched: 09/21/2026, 22:31:32 UTC

Last updated: 09/21/2026, 22:35:16 UTC

Views: 6

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses