CVE-2026-73559: vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions Complet
Summary
vLLM (an AI model serving system) versions 0.19.0 to 0.26.0 have a vulnerability where the /v1/completions endpoint accepts unlimited lists of prompts, causing the system to create excessive processing tasks. An authenticated attacker could send a single request with many prompts to overwhelm the server's CPU, memory, and scheduling capacity, making it unavailable to other users.
Solution / Mitigation
This issue is fixed in version 0.26.0. Users should update vLLM to version 0.26.0 or later.
Vulnerability Details
6.5(medium)
EPSS: 0.0%
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
network
low
low
none
August 13, 2026
Classification
Affected Vendors
Related Issues
CVE-2026-63086: text-generation-inference through 3.3.7 contains a server-side request forgery (SSRF) vulnerability in the OpenAI-compat
CVE-2024-37052: Deserialization of untrusted data can occur in versions of the MLflow platform running version 1.1.0 or newer, enabling
Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-73559
First tracked: August 13, 2026 at 02:08 PM
Classified by LLM (prompt v3) · confidence: 95%