p PatchFirst

CVE-2026-100652

CVE-2026-100652 · vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

This page contains facts from public vulnerability sources. Check the original advisory before updating.

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.

CVSS 8.2 · High · EPSS 0.4% · Fix available

Published
Updated

Stack: python

Affected products and versions

  • vllm

    Versions
    • ≥ 0.22.0, < 0.24.0: Affected (semver)
    • 0.24.0: Not affected (semver)

    Update to 0.24.0

  • vllm PyPI

    Versions
    • 0.22.0
    • 0.22.1
    • 0.23.0
    Affected ranges
    • ECOSYSTEM: ≥ 0.22.0, < 0.24.0

    Update to 0.24.0

Original sources

Check your server →