Description
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
vllm-project vllm
Default version status: unaffected
0.8.5 to < 0.31.0affected0.31.0unaffected
pkg:pypi/vllm