| Component | vLLM |
| Severity | medium (CVSS 5.3) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L |
| Published (NVD) | 2026-08-25 |
| Last modified | 2026-09-29 |
| Affected versions | vllm < 0.27.0 |
| Fixed in | 0.27.0 |
| Weakness | CWE-400 |
| CISA KEV | not listed |
NVD description
vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in its decode path. Unauthenticated attackers can activate DeepStream at request time to initialize the process-wide GPU decode pool and submit video that bypasses resource controls, causing partial denial of service for concurrent requests.
What to do
- Upgrade vLLM to
0.27.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-78684
- https://github.com/vllm-project/vllm/security/advisories/GHSA-cqm8-jxg6-fqfq
- https://github.com/vllm-project/vllm/commit/e23b19309b8705b21c3b3ff4129c9974ba15a419
- https://www.vulncheck.com/advisories/vllm-before-denial-of-service-via-deepstream-backend
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...