CVE-2026-93436
highvLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments.
Vendor / product: Vllm — vllm
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.
CVSS
7.5
7.5 (CVSS v3.1)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H Severity source: NVD CVSS v3.1 (disclosure@vulncheck.com)
Timeline (UTC)
Published: 2026-09-17 23:18
Modified: 2026-09-28 18:37
NVD status: Analyzed
Last synced 2 days ago
Verified against the source API 2026-10-27 06:54 UTC
Exploitation
Not listed in CISA KEV (as of last catalog sync)
Absence from KEV does not mean a CVE is not exploited. Exploitation status: unknown (no authoritative evidence in our sources).
Affected products
vllm / vllm ≤0.29.0
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
Patch / mitigation: https://github.com/vllm-project/vllm/pull/55677
References
- https://github.com/vllm-project/vllm disclosure@vulncheck.com
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connecto... disclosure@vulncheck.com
- https://github.com/vllm-project/vllm/pull/55677 disclosure@vulncheck.com
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-re... disclosure@vulncheck.com
Data sources
NVD CVE API 2.0 — fetched 2026-10-27 06:54 UTC · record ↗