GHSA-hq63-vm56-2666HighCVSS 7.5
vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI...
🔗 CVE IDs covered (1)
📋 Description
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.
🔗 References (7)
- https://nvd.nist.gov/vuln/detail/CVE-2026-94626
- https://github.com/vllm-project/vllm/pull/51137
- https://github.com/vllm-project/vllm
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/utils.py#L569-L573
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/metadata.py#L277
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-unvalidated-nixl-tp-size
- https://github.com/advisories/GHSA-hq63-vm56-2666