CVE-2026-93436CWE-401

CVE-2026-93436

High · published September 18, 2026

CVSS v3.1
7.5
EPSS
1%
Percentile
54.6
In the wild
Unconfirmed
What it is

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.

The record
Technical detail
CVSS v3.1
7.5 · HIGH
Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS v4.0
8.7 · 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
EPSS
0.00755 · 54.6th percentile
Weakness
CWE-401 · Missing Release of Memory after Effective Lifetime
Published
2026-09-18T03:18Z
Affected products (1)
ProductVersionsFixed in
vllm/vllm≤ 0.29.0—
References (4)
https://github.com/vllm-project/vllm · [email protected]https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181 · [email protected]https://github.com/vllm-project/vllm/pull/55677 · [email protected]https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests · [email protected]
EPSS history
Timeline
  • 19 SEP 03:55Z
    EPSS moved — → 1%
    epss
  • 17 SEP 22:15Z
    vLLM through 0.29.0 Memory Exhaustion via Rejected Requests
    cvelistv5