| Component | vLLM |
| Severity | medium (CVSS 5.6) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L |
| Published (NVD) | 2026-04-27 |
| Last modified | 2026-08-25 |
| Affected versions | vllm <= 0.19.0 |
| Fixed in | see the vendor advisory |
| Weakness | CWE-908 |
| CISA KEV | not listed |
NVD description
A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."
What to do
- NVD lists no fixed version yet: follow the vendor advisory below and keep vLLM off the public internet until a fix ships.
- Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-7141
- https://vuldb.com/submit/801297
- https://vuldb.com/vuln/359740
- https://github.com/vllm-project/vllm/issues/39146
- https://github.com/vllm-project/vllm/issues/39146#issue-4215090365
- https://vuldb.com/cve/CVE-2026-7141
- https://vuldb.com/vuln/359740/cti
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...