vLLM
vLLM from 0.8.5 before 0.31.0 Cross-Tenant DoS via Uninitialized LogprobsTensors
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.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS8.3high · scored by CNA · CWE-908
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
vllm-project vllm
- >= 0.8.5, < 0.31.0
Fixed in 0.31.0
Mitigation
Upgrade vllm to 0.31.0 or later.
References
- Vendor advisory github.com/vllm-project/vllm/security/advisori…
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.