CVE-2026-94626
HIGHCVSS 7.5Description
vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tp_size values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel OOM-kill of the decode worker process.
Timeline
Published:September 21st, 2026 10:17 PM
Last modified:September 29th, 2026 12:46 PM
CVSS Scoring
CVSS v3: 7.5 (HIGH)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Affected Software
From NVD CPE configuration data
Vendors
vllm
Products
vllm
Weaknesses (CWE)
References & Reports
Advisories, patches, and third-party reports
- https://github.com/vllm-project/vllmProduct
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/utils.py#L569-L573Product
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.py#L277Product
- https://github.com/vllm-project/vllm/pull/51137Issue Tracking
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-unvalidated-nixl-tp-sizeThird Party Advisory
Source: NIST NVD · Data may lag official sources by up to one minute