| Component | vLLM |
| Severity | medium (CVSS 5.5) |
| CVSS vector | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| Published (NVD) | 2026-08-11 |
| Last modified | 2026-09-24 |
| Affected versions | vllm_hardware < 0.16.0 vllm_hardware = 0.19.0 vllm_hardware = 0.19.1 |
| Fixed in | 0.16.0 |
| Weakness | CWE-20 |
| CISA KEV | not listed |
NVD description
Improper input validation for some vLLM Hardware Plugin for Intel(R) Gaudi(R) software before version 0.16.0 within Ring 3: User Applications may allow a denial of service. Authorized adversary with an authenticated user combined with a low complexity attack may enable denial of service. This result may potentially occur via local access when attack requirements are not present without special internal knowledge and requires no user interaction. The potential vulnerability may impact the confidentiality (none), integrity (none) and availability (high) of the vulnerable system, resulting in subsequent system confidentiality (none), integrity (none) and availability (none) impacts.
What to do
- Upgrade vLLM to
0.16.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...