Resource exhaustion in Vllm-Project Vllm

CVE-2026-71486

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.

Vulnerability class: DoS (Denial of Service)

Published · last modified .

CVSS v3 metric

CVSS v3 base score 4.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L.

EPSS exploit prediction

EPSS: 0.005 (38.0th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 38th percentile — 38.0% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2026-71486: held from 0.003 to 0.005.

EPSS over last 30 days · oldest: 0.003 · newest: 0.005 · change: +0.001

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-71486?
CVE-2026-71486 is a medium-severity vulnerability in Vllm-Project Vllm, classified under Uncontrolled Resource Consumption. CVSS score: 4.3/10. Published 2026-08-17.
How severe is CVE-2026-71486?
Medium severity. CVSS v3 base score is 4.3 out of 10.