Medium 4.3Published Aug 17, 2026

CVE-2026-71486vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

Updated under an hour ago (Oct 27, 2026, 7:30 AM ET)

Does this affect you?

It affects vllm-project vllm and 1 other product. Add what you run to find out whether that includes you.

No exploitation reported and no EPSS estimate yet.

Do this next

Start free and add your stack

Free account, 1 product

Every CVE for vllm-project vllm

Exploited in the last 30 days

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.

CVSS: 4.3 MEDIUM (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Weakness (CWE): CWE-400, CWE-770
Known exploited: Not in CISA's KEV catalog
EPSS (exploitation in the next 30 days): Not loaded for this CVE
Assigned by: GitHub_M
NVD analysis: Analyzed
Record last updated: Aug 18, 2026
First seen by InfoSec Signals: Oct 9, 2026

Affected products

Affected products

vllm-project vllm vllm_project:vllm (from the name)	before 0.26.0	CNA record
vllm vllm vllm:vllm	before 0.26.0	NVD

References

References

https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff	x-refsource-confirm, exploit, vendor-advisory, mitigation
https://github.com/vllm-project/vllm/pull/47260	x-refsource-misc, issue-tracking, patch
https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b	x-refsource-misc, patch
https://github.com/vllm-project/vllm/releases/tag/v0.26.0	x-refsource-misc, release-notes

The CVE record on cve.org NVD's entry

The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.