Resource exhaustion in Vllm
CVE-2026-100649
vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments. Unauthenticated attackers can select different sampler subclasses in video requests to exceed configured decoder limits and exhaust unaccounted GPU memory.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 3.7 (Low). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L.
EPSS exploit prediction
EPSS: 0.003 (27.9th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 28th percentile — 27.9% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.003 · newest: 0.003 · change: 0.000
Affected products
Weakness classification (CWE)
References
- GitHub Security Advisory (GHSA-j682-9xp5-rrf3) (vendor-advisory, Vendor Advisory)
- VulnCheck Advisory: vLLM before 0.29.0 Resource Limit Bypass via Sampler Subclass (Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-100649?
- CVE-2026-100649 is a low-severity vulnerability in Vllm, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 3.7/10. Published 2026-09-26.
- How severe is CVE-2026-100649?
- Low severity. CVSS v3 base score is 3.7 out of 10.