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.

A flaw was found in vLLM. An authenticated API client can exploit derender endpoints by providing oversized GenerateResponse objects. These endpoints process the objects without enforcing output bounds or response-size limits. This can lead to excessive consumption of CPU and memory resources, resulting in a Denial of Service (DoS).

Red Hat AI Inference Server Fix deferred rhaiis/vllm-cpu-rhel9 Red Hat AI Inference Server Fix deferred rhaiis/vllm-cuda-rhel9 Red Hat AI Inference Server Fix deferred rhaiis/vllm-neuron-rhel9 Red Hat AI Inference Server Fix deferred rhaiis/vllm-rocm-rhel9 Red Hat AI Inference Server Fix deferred rhaiis/vllm-spyre-rhel9 Red Hat AI Inference Server Fix deferred rhaiis/vllm-tpu-rhel9 Red Hat AI Inference Server Fix deferred rhaii/vllm-cpu-rhel9 Red Hat AI Inference Server Fix deferred rhaii/vllm-cuda-rhel9 Red Hat AI Inference Server Fix deferred rhaii/vllm-gaudi-rhel9 Red Hat AI Inference Server Fix deferred rhaii/vllm-neuron-rhel9 Red Hat AI Inference Server Fix deferred rhaii/vllm-rocm-rhel9 Red Hat AI Inference Server Fix deferred rhaii/vllm-spyre-rhel9 Red Hat AI Inference Server Fix deferred rhaii/vllm-tpu-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 Fix deferred rhelai3/bootc-aws-cuda-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 Fix deferred rhelai3/bootc-azure-cuda-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 Fix deferred rhelai3/bootc-azure-rocm-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 Fix deferred rhelai3/bootc-cuda-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 Fix deferred rhelai3/bootc-gaudi-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 Fix deferred rhelai3/bootc-gcp-cuda-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 Fix deferred rhelai3/bootc-rocm-rhel9 Red Hat OpenShift AI (RHOAI) Fix deferred rhoai/odh-kserve-agent-rhel9 Red Hat OpenShift AI (RHOAI) Fix deferred rhoai/odh-kserve-controller-rhel9 Red Hat OpenShift AI (RHOAI) Fix deferred rhoai/odh-kserve-router-rhel9 Red Hat OpenShift AI (RHOAI) Fix deferred rhoai/odh-kserve-storage-initializer-rhel9 Red Hat OpenShift AI (RHOAI) Fix deferred rhoai/odh-llm-d-kv-cache-rhel9 Red Hat OpenShift AI (RHOAI) Fix deferred rhoai/odh-th-torch-cuda-py312-rhel9 Red Hat OpenShift AI (RHOAI) Fix deferred rhoai/odh-vllm-gaudi-rhel9 https://www.cve.org/CVERecord?id=CVE-2026-71486 https://nvd.nist.gov/vuln/detail/CVE-2026-71486 https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b https://github.com/vllm-project/vllm/pull/47260 https://github.com/vllm-project/vllm/releases/tag/v0.26.0 https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff