CVE-2026-116180
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- None
- Integrity
- None
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
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.
- Record
CVE-2026-116180- CVSS 4.0
- 8.3 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H - CVSS 3.1
- 7.7 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H - Weakness
- CWE-908
- Updated
- 2026-11-02
EUVDEUVD-2026-109441
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.
- Record
EUVD-2026-109441- CVSS 4.0
- 8.3 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-v8gv-gxpf-cg62
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in 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.
- Record
GHSA-v8gv-gxpf-cg62- CVSS 4.0
- 8.3 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - CVSS 3.1
- 7.7 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H - Weakness
- CWE-908
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2026-116180- CVSS 4.0
- 8.3 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - CVSS 3.1
- 7.7 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H - Weakness
- CWE-908
- Updated
- 2026-11-02
OSV
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.
- Record
CVE-2026-116180- CVSS 4.0
- 8.3 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H - Weakness
- CWE-908
- Updated
- 2026-11-02
Affected products
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-116180 is a high vulnerability (CVSS 8.3) in Vllm, published October 25, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.25%, the 17th percentile. No source names a fixed version.
References
github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729-88vg
vulncheck.com/advisories/vllm-from-0.8.5-before-0.31.0-cross-tenant-dos-via-uninitialized-logprobstensors
nvd.nist.gov/vuln/detail/CVE-2026-116180