Skip to content
MediumVulnerability

GHSA-58v5-2m8f-94pr: vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

Published
Record updated
View JSON
Affected
  • vllm >= 0.23.0rc2, < 0.30.0
Fixed in
0.30.0
  • released September 22, 2026, 13 days before disclosure
Known exploitation
Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS
0.3%

Summary

vLLM's OpenAI-compatible chat endpoint accepts request-level `media_io_kwargs`, so a caller can select the GLMGA video sampler and set large `fps` and `max_frames` values. GLMGA builds and deduplicates an attacker-sized index list before frame reads, so a tiny valid video with compact JSON options can consume disproportionate CPU and memory in the shared media-loading executor and delay unrelated media requests. The demonstrated impact is partial denial of service, with no memory corruption, data disclosure or code execution claimed.

Mitigation

Validate request-level video sampling options before dispatching work to the media executor. Enforce conservative absolute limits for `fps`, `max_frames`, and especially the computed candidate count.