---
id: "GHSA-3cgq-c484-rx5j"
kind: "vulnerability"
aliases: ["GHSA-3cgq-c484-rx5j"]
title: "Duplicate Advisory: vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs"
severity: "high"
cvss: 7.5
epss: null
exploited: false
status: "withdrawn"
category: "ai-tooling"
products: [{"name": "vllm", "fixed": [], "affected": ">= 0.7.3, < 0.31.0", "ecosystem": "pypi"}]
ecosystems: ["pypi"]
tags: ["ai-tooling", "cwe-400", "model-serving", "python", "self-hosted", "vllm"]
not_affected_if: ["multimodal-models-not-used", "version-outside-range"]
published_at: "2026-10-21T03:32:16+00:00"
first_seen_at: "2026-10-23T20:59:05+00:00"
updated_at: "2026-10-23T21:00:17+00:00"
sources: [{"source": "ghsa", "url": "https://github.com/advisories/GHSA-3cgq-c484-rx5j", "first_seen_at": "2026-10-23T20:59:05+00:00"}]
---

# Duplicate Advisory: vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs

vLLM, an LLM serving library, accepts per-request mm_processor_kwargs without validation, so a remote client can set huge image, patch, crop or frame counts. This exhausts memory and can crash the shared server for all users.

_Summary, check and fix written by a model from the sources; labelled as such._

## Affected

- pypi:vllm affected >= 0.7.3, < 0.31.0 fixed ?

## How to check

Run pip show vllm and check whether the version is >= 0.7.3 and < 0.31.0.

## Fix

Upgrade vllm to 0.31.0 or later, per the duplicate advisory GHSA-gx7p-2j49-hfq4 which this entry points to.

## Timeline

- 2026-10-23T20:59:05+00:00 ghsa https://github.com/advisories/GHSA-3cgq-c484-rx5j

## From the sources

## Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-gx7p-2j49-hfq4. This link is maintained to preserve external references.

## Original Description
vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters by supplying per-request mm_processor_kwargs. Attackers can set large image size, patch count, crop count, or frame count values in Isaac, InternVL, H2OVL, and other processors to exhaust memory and terminate the shared server.

---

_Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai_