CVE-2026-100652

Summary

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

Affected Software

VendorProductVersion RangeStatus
vllm-projectvllm0.22.0 < 0.24.0affected
vllm-projectvllm0.24.0unaffected

Weaknesses

  • CWE-20: Improper Input Validation

References