Skip to content
Threat Feed
Subscribe

Vendor

VLLM

1 brief RSS
low advisory

vLLM Remote Denial of Service via Invalid Token Reinjection

A frontend-legal multi-request speculative workload can cause vLLM to produce an out-of-vocabulary recovered token, which is then converted to an invalid value (-1) and reinjected into the drafting input IDs, leading to a GPU device-side assert and crashing the vLLM engine, causing a service-wide denial of service through a specific gRPC request sequence.

vLLM denial-of-service vulnerability LLM AI python server-side
1r 1t 1c