CVE-2026-93436

high

Description

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.

References

https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests

https://github.com/vllm-project/vllm/pull/55677

https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181

https://github.com/vllm-project/vllm

Details

Source: Mitre, NVD

Published: 2026-09-17

Updated: 2026-09-22

Risk Information

CVSS v2

Base Score: 7.8

Vector: CVSS2#AV:N/AC:L/Au:N/C:N/I:N/A:C

Severity: High

CVSS v3

Base Score: 7.5

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Severity: High

CVSS v4

Base Score: 8.7

Vector: 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

Severity: High

EPSS

EPSS: 0.00538