vllm vulnerability

What happened

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.

Affected versions

vllm: 0 through 0.29.0 (semver) Fixed: See vendor advisory.

Why it matters

Review the vendor advisory and exposure of the affected product to determine operational impact.

Detection & mitigation

• Apply vendor-provided updates or mitigations.
• Review affected product exposure and access logs.