CVE-2026-34756

high Red Hat
CVSS v3 Base Score
6.5
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Characteristics
Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Confidentiality
None
Integrity
None
Availability
High
Published: April 6, 2026 (37 days ago)
Last Modified: April 6, 2026
Vendor: Red Hat
Source: REDHAT

Description

A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). An unauthenticated attacker can exploit this vulnerability by sending a specially crafted HTTP request with an excessively large 'n' parameter to the vLLM OpenAI-compatible API server. This can lead to a Denial of Service (DoS) by consuming excessive memory and blocking the system's event loop, causing the server to crash.

CWE

CWE-1284

Affected Products

Red Hat AI Inference ServerRed Hat Enterprise Linux AI (RHEL AI) 3Red Hat OpenShift AI (RHOAI)

References

🔗 bugzilla.redhat.com 🔗 www.cve.org 🔗 nvd.nist.gov 🔗 github.com 🔗 github.com