CyberRota Analysis
AI-GeneratedThe vLLM inference engine is vulnerable due to its endpoints allowing authenticated API clients to send oversized GenerateResponse objects, which can lead to excessive CPU and memory consumption before any response size limits are enforced. This can result in degraded performance or denial of service for the application. Organizations using versions prior to 0.26.0 should prioritize upgrading 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 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.