Junglewise Threat Intelligence

CVE-2026-54234: vLLM denial of service via invalid recovered token in speculative decoding

CVE-2026-54234 · Severity: high · CVSS 7.5 · Published 2026-07-06

Technologies: vllm (PyPI), vLLM Project vllm. Vendors: PyPI, vLLM Project.

Executive brief

vLLM is a high-throughput engine for serving large language models. A vulnerability in its speculative decoding feature allows a remote attacker to crash the engine by sending a specific sequence of requests. This results in a service-wide denial of service, interrupting all active users and preventing new requests until the system is manually restarted.

Technical details

A vulnerability exists in vLLM's speculative decoding implementation, specifically within the rejection sampling and next-token preparation logic. When processing certain multi-request workloads, the rejection sampler can produce a recovered token ID equal to the model's 'vocab_size'. This out-of-vocabulary value is incorrectly converted to -1 and reinjected into the live model input IDs for the next drafting step. When the drafting or attention path (e.g., flash_attn_varlen_func) later consumes this invalid token, it triggers a CUDA device-side assertion, crashing the entire vLLM worker. The issue is reachable via public gRPC interfaces using a sequence of Generate and Abort requests. This was patched in version 0.24.0.

Affected products

  • vLLM Project vLLM >= 0.17.1, < 0.24.0

Timeline

  • 2026-07-02: disclosed
  • 2026-07-17: advisory: GitHub Advisory published
  • 2026-07-17: patched

References

Related threats