CVE-2026-116180
highvLLM from 0.8.5 before 0.31.0 has a denial of service flaw.
Vendor / product: Vllm — vllm
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.
CVSS
7.7
7.7 (CVSS v3.1)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H Severity source: NVD CVSS v3.1 (disclosure@vulncheck.com)
Timeline (UTC)
Published: 2026-10-25 14:16
Modified: 2026-10-28 15:40
NVD status: Analyzed
Last synced 1 day ago
Verified against the source API 2026-10-28 16:01 UTC
Exploitation
Not listed in CISA KEV (as of last catalog sync)
Absence from KEV does not mean a CVE is not exploited. Exploitation status: unknown (no authoritative evidence in our sources).
Affected products
vllm / vllm ≥0.8.5 <0.31.0
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
Patch / mitigation: https://github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729-88vg
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729-88vg disclosure@vulncheck.com
- https://www.vulncheck.com/advisories/vllm-from-0.8.5-before-0.31.0-cross-tenant-dos-via-un... disclosure@vulncheck.com
Data sources
NVD CVE API 2.0 — fetched 2026-10-28 16:01 UTC · record ↗