Public mode

No access to your tenant or devices. Every item links to its source. What this means

Sources need attention Customize Public modeDiscuss ChangeIntel on Discord

vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

CVSS 3.1 4.3 MEDIUMCheck source for fixed versionsKEV status unknown

cve-program · CVE-2026-71486

Published

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.

Read the publisher's advisory

Affected versions, risk and source history

Related advisories and sources

Publishers link these advisories through the identifiers shown below. A shared identifier or date alone does not tell you whether your software is affected or whether the advisories describe the same cause.

CVE-2026-71486 · CVE overview and exploitation status

cve-program · CVE-2026-71486

Related changes

Linked by CVE identifier

No related changes are available here.

ChangeIntel

An IT change radar: releases, security, known issues, retirements, documentation changes, and service status from public sources. Every item links to supporting evidence; dates and statuses can change after they are read.

Sources read 21 Nov 20:28 UTC · 274 of 275 readable · 270 fully read · documentation 469/469 current