CyberRota Analysis
AI-GeneratedThe vulnerability allows attackers to exploit the request-level media_io_kwargs field in vLLM prior to version 0.30.0, enabling them to supply excessively large values for the fps and max_frames options. This can lead to resource exhaustion, consuming disproportionate CPU time and memory in the shared media-loading executor, potentially impacting system performance and availability. Organizations using vLLM for large language model inference and serving should prioritize upgrading to version 0.30.0 to mitigate this risk.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
Related CVEs
Other vulnerabilities affecting the same vendor(s)