vulnti.work

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. …

Medium CVSS 5.9
CVECVE-2026-100652
First seen2026-09-26 16:31 UTC
Disclosed2026-09-26 14:16 UTC
Last updated2026-09-26 16:31 UTC
Channel statusauto

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.

In-depth triage

No in-depth report has been generated yet (DR-003 v2 AI pipeline is under construction).

Sources

  • NVD DATABASE

Original Links

Timeline

  1. nvd_ingest NVD