CVE-2026-94626

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.

Affected Platforms

Weakness Type

CWE-789

References

• https://github.com/vllm-project/vllm
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/k…
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/k…
• https://github.com/vllm-project/vllm/pull/51137
• https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-u…