Resource exhaustion in Vllm
CVE-2026-34755
vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.008 (56.3th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 56th percentile — 56.3% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.005 · newest: 0.008 · change: +0.004
Affected products
- Vllm
- Vllm-Project Vllm — versions >= 0.7.0, < 0.19.0
Weakness classification (CWE)
References
- github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p (Patch, Vendor Advisory)
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
- 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Frequently asked questions
- What is CVE-2026-34755?
- CVE-2026-34755 is a medium-severity vulnerability in Vllm, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 6.5/10. Published 2026-04-06.
- How severe is CVE-2026-34755?
- Medium severity. CVSS v3 base score is 6.5 out of 10.