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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-400",
"CWE-770"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/71xxx/CVE-2026-71486.json"
}