CVE-2026-71486

Published: Ago 17, 2026 Last Modified: Ago 17, 2026

ExploitDB:

Other exploit source:

Google Dorks:

MEDIUM 4,3

Source: [email protected]

Attack Vector: network

Attack Complexity: low

Privileges Required: low

User Interaction: none

Scope: unchanged

Confidentiality: none

Integrity: none

Availability: low

Description

AI Translation Available

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.

400

Uncontrolled Resource Consumption

Draft

Abstraction: Class Structure: Simple

Common Consequences

Security Scopes Affected:

Availability Access Control Other

Potential Impacts:

Dos: Crash, Exit, Or Restart Dos: Resource Consumption (Cpu) Dos: Resource Consumption (Memory) Dos: Resource Consumption (Other) Bypass Protection Mechanism Other