---
id: "CVE-2026-116179"
kind: "vulnerability"
aliases: ["CVE-2026-116179"]
title: "vLLM: API clients can bypass frame cap and exhaust memory"
severity: "high"
cvss: 8.7
epss: null
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["ai-tooling", "llm-serving", "self-hosted", "vllm"]
not_affected_if: ["auth-required", "text-only-models", "trusted-clients-only"]
published_at: "2026-10-25T14:16:57+00:00"
first_seen_at: "2026-10-25T14:41:23+00:00"
updated_at: "2026-10-25T14:42:17+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-116179", "first_seen_at": "2026-10-25T14:41:23+00:00"}]
---

# vLLM: API clients can bypass frame cap and exhaust memory

vLLM versions from 0.18.0 before 0.31.0 let API clients override the video frame-count limit through media_io_kwargs. Setting num_frames to -1 with a large inline video makes the server decode every frame, which exhausts memory and crashes the API frontend.

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

## How to check

- Check the installed version with `pip show vllm` or `python -c "import vllm; print(vllm.__version__)"`; versions from `0.18.0` up to but not including `0.31.0` are affected.
- Check whether the OpenAI-compatible API accepts video input with inline base64 data from untrusted clients.

## Fix

- Upgrade vLLM to `0.31.0` or later.
- Until upgraded, restrict API access to trusted clients or reject requests that set media_io_kwargs for video.

## Timeline

- 2026-10-25T14:41:23+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-116179

## From the sources

vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding num_frames through media_io_kwargs. Attackers can set num_frames to -1 with a large inline video so VideoMediaIO.load_base64 decodes every frame, exhausting memory and crashing the API frontend.

---

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