Answer in brief
CVE-2026-34755 records a Medium severity (CVSS 6.5) vulnerability in vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic), vllm (pip), vllm (pypi). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 6.5. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps vllm-project/vllm (generic), vllm (pip), vllm (pypi). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| vllm-project/vllmgeneric | >= 0.7.0, < 0.19.0 | Not reported |
| vllmpip | >=0.7.0,<0.19.0 | 0.19.0 |
| vllmpypi | >=0.7.0 <0.19.0 | 0.19.0 |
Published upstream
Apr 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 20, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Jun 11, 2026
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.
Quoted source text, attributed separately from HOL analysis.