CVE-2026-78684: vLLM before 0.27.0 fails to properly classify DeepStream as a GPU backend and omits pixel-limit enforcement in
CVE-2026-78684 is a medium-severity flaw (CVSS 5.3) affecting vllm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
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.
Why this priority
- Remotely exploitable, no login, no user action
A fixed release or distro patch exists.
Risk facts
| CVSS score | 5.3 (Medium) |
| Attack vector | Network (remote) |
| Attack complexity | Low |
| Privileges needed | None |
| User interaction | None |
| EPSS exploit chance | 0.6% (top 51%) |
| CISA exploited list | No |
| Weakness | CWE-400 |
| Published | 2026-08-25 |
| Last modified | 2026-09-29 |
Last updated 2026-09-29 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score
Am I affected?
Timeline
- Published CVE record published
- Updated Record last modified
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.
Quick answers
How do I fix CVE-2026-78684?
vllm: upgrade to 0.27.0. Exact commands for each OS are on this page.
Is CVE-2026-78684 being exploited?
CVE-2026-78684 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.
What does CVE-2026-78684 affect?
CVE-2026-78684 affects vllm. Severity is medium (CVSS 5.3). 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
How urgent is CVE-2026-78684?
Priority 36/100. Remotely exploitable, no login, no user action
Related CVEs
- CVE-2026-5497 HIGH 7.5 UPGRADE vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to u
- CVE-2026-48746 CRITICAL 9.1 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54232 HIGH 8.8 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-41523 HIGH 7.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54236 MEDIUM 5.3 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)