{"id":"CVE-2026-100649","title":"vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent counter increments","summary":"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 subclas…","severity":"low","cvss":3.7,"cvssVector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L","cwe":["CWE-770"],"vendor":"vllm","product":"vllm","affected":["vllm < 0.29.0"],"patched":["vllm 0.29.0"],"published":"2026-09-26","updated":"2026-10-06","sourceUpdated":"2026-10-06T19:37:35.050","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-100649","references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-j682-9xp5-rrf3","label":"disclosure@vulncheck.com"},{"url":"https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-limit-bypass-via-sampler-subclass","label":"disclosure@vulncheck.com"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-100649.json"},{"url":"https://access.redhat.com/security/cve/CVE-2026-100649"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2541914"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-100649"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-100649"}],"tags":["nvd","cve.org","csaf","vex","red-hat"],"epss":0.00341,"epssPercentile":0.27436,"ssvc":{"exploitation":"none","automatable":"no","technicalImpact":"partial","timestamp":"2026-10-02T18:00:00.754862Z"},"ingestedAt":"2026-09-26T13:33:20.920Z","slug":"CVE-2026-100649","body":"## Overview\n\nvLLM 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.\n\n## Affected\n\n- `vllm < 0.29.0`\n\n## Remediation\n\nUpgrade past the affected range:\n\n- `vllm 0.29.0`\n\n## Vendor advisories\n\n- **Red Hat VEX** · Low · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-10-06 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-100649.json)","depth":"sunlit","depthScore":20,"depthScoreParts":{"impact":20.4,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}