CVE-2026-34755Medium· 6.5▾ SunlitvLLM 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 JPE…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 35.8 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Jul 7.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Last analysed / modified upstream
0.4%
0.4% → 0.5%
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.
vllm >= 0.7.0, < 0.19.0Upgrade past the affected range:
vllm 0.19.0Affected packages:
vllm >= 0.7.0, < 0.19.0Patched in:
vllm 0.19.0Connected by shared product, vendor, weakness, or advisory.
CVE-2026-34756Medium· 6.5vLLM is an inference and serving engine for large language models (LLMs)
CVE-2026-48746Critical· 9.1vLLM is an inference and serving engine for large language models (LLMs)
CVE-2026-69147Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-57173Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-71486Medium· 4.3vLLM is an inference and serving engine for large language models
CVE-2026-94626High· 7.5vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory