High
vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.
Announced Group revision 1
Original source ↗CVE-2026-93436
Primary source · Revision 1
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
Security context
Source reference: cve:CVE-2026-93436
vllm
Source reference: /containers/cna/affected/0/product
- Affected versions
- Not stated in this record
- Fixed versions
- Not stated in this record
- Prerequisites
- Not stated in this record
Structured affected-version data
Original package identities and version rules from this source.
[
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"status": "affected",
"version": "0",
"versionType": "semver",
"lessThanOrEqual": "0.29.0"
}
],
"packageURL": "pkg:pypi/vllm",
"defaultStatus": "unaffected"
}
]- Related CVEs
- CVE-2026-93436
Source reference:
/cveMetadata/cveId
Publisher severity
high
Source reference: /containers/cna/metrics
- Event
- #1702 · Revision 1
- Added to Heist Feed
- Publisher date