CVE-2026-71486

Medium

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.

SeverityMedium

CVSS4.3

Exploit probability—

ProductVllm

PublishedAug 17, 2026

First seenAug 17, 2026

Weakness typeCWE-400Uncontrolled resource consumption CWE-770Allocation of resources without limits

How to fix

Update

vllm vllm0.26.0 or later
vllm0.26.0 or later

Affected products

Product	Affected versions	Fixed in
vllm vllm	v < 0.26.0	0.26.0
vllmPyPI	v < 0.26.0	0.26.0

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.