CVE-2026-109227

SGLang through 0.5.21 Memory Exhaustion DoS via Qwen-VL Video Preprocessing

Published Oct 12, 2026 CVSS 4.0 · 8.7 High EPSS < 1% KEV · Not listed
Description
SGLang through 0.5.21 contains an unbounded memory allocation vulnerability in preprocess_video in qwen_vl.py that decodes frames at full source resolution before applying max_pixels limits. Remote attackers can submit high-resolution videos to /v1/chat/completions on Qwen-VL deployments, and concurrent requests exhaust worker memory causing denial of service.

Analysis

AI-generated

Technical impact

SGLang versions up to 0.5.21 allocate memory unbounded during video preprocessing in the qwen_vl module. The implementation decodes frames at their full source resolution before any pixel‑count limits are applied, creating a flaw that falls under CWE‑770. When high‑resolution videos are submitted to the Qwen‑VL chat completion endpoint, the server can consume all available worker memory, causing the application to become unresponsive and effectively denying service to legitimate users.

Affected Systems

The affected product is the sgl‑lang framework distributed by sgl‑project, specifically versions up through 0.5.21. Hosts running Qwen‑VL deployments that expose the /v1/chat/completions API and use the SGLang 0.5.21 code base are vulnerable.

Risk and Exploitability

The CVSS score of 8.7 classifies this flaw as High severity. The EPSS score is not available, but the exploit requires a target that accepts arbitrary‑resolution video uploads and a vulnerability in the preprocessing pipeline; thus the attack surface is relatively narrow. Because the flaw leads to denial of service rather than data compromise, the immediate impact is availability degradation rather than confidentiality or integrity loss. The lack of a KEV listing suggests no known large‑scale exploitation, yet the inherent resource exhaustion risk remains for any exposed Qwen‑VL instance.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade SGLang to a version newer than 0.5.21 that addresses the preprocessing memory allocation issue.
  • Modify the preprocessing pipeline or API to enforce a maximum resolution or pixel count before decoding frames.
  • Implement rate limiting or concurrency controls on the /v1/chat/completions endpoint to prevent simultaneous high‑resolution video submissions.
  • Monitor worker memory usage and set alerts for anomalous growth that could indicate an ongoing denial‑of‑service attempt.

Generated by OpenCVE AI on October 12, 2026 at 15:36 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Sgl-project
Sgl-project sglang
Vendors & Products Sgl-project
Sgl-project sglang
Type Values Removed Values Added
Description SGLang through 0.5.21 contains an unbounded memory allocation vulnerability in preprocess_video in qwen_vl.py that decodes frames at full source resolution before applying max_pixels limits. Remote attackers can submit high-resolution videos to /v1/chat/completions on Qwen-VL deployments, and concurrent requests exhaust worker memory causing denial of service.
Title SGLang through 0.5.21 Memory Exhaustion DoS via Qwen-VL Video Preprocessing
First Time appeared Lmsys
Lmsys sglang
Weaknesses CWE-770
CPEs cpe:2.3:a:lmsys:sglang:*:*:*:*:*:*:*:*
Vendors & Products Lmsys
Lmsys sglang
References
Metrics cvssV3_1

{'score': 7.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'}

cvssV4_0

{'score': 8.7, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N'}

Weaknesses
  • CWE-770

    Allocation of Resources Without Limits or Throttling

Sources

Status
PUBLISHED
Assigner
VulnCheck
Published
Updated
Oct 18, 2026, 11:46 AM
Reserved
Oct 12, 2026, 1:46 PM
Status
Deferred
Published
Oct 12, 2026, 2:17 PM
Modified
Oct 18, 2026, 12:17 PM