vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

[ Description ]Official description

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.

[ Fixes ]Fixes and patches

• vllm 0.30.0Fixed version · GitHub Advisories · pip package vllm: upgrade to 0.30.0 or later (affected >= 0.23.0rc2, < 0.30.0)
• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD

[ Advisories ]Government CERT advisories

• BSI CERT-Bund5 Oct 2026WID-SEC-2026-3754

  vllm: Multiple vulnerabilities allow denial of service Translated from German

  CVE-2026-105758CVE-2026-105760CVE-2026-105759+2 more CVEs

[ Packages ]Affected open-source packages

• vllm pipAffected >= 0.23.0rc2, < 0.30.0 · fixed in 0.30.0 · GHSA-58v5-2m8f-94pr

[ References ]References

• github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7Patch
• github.com/vllm-project/vllm/pull/54935Issue TrackingPatch
• github.com/vllm-project/vllm/releases/tag/v0.30.0Release Notes
• github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94prMitigationVendor Advisory