CVE-2026-71486

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.

Severity
MEDIUM
CVSS v3
4.3
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L · source cna
Exploit chance (EPSS)
0.374%
chance of exploitation in the next 30 days
higher than 31.8% of scored CVEs · 2026-11-17
CISA KEV
Not listed
Public exploit code
Yes
Exploit references (NVD and CNA): 1
Metasploit modules: 0
Nuclei templates: 0

Weakness

CISA SSVC decision points

Exploitationnone
Automatableno
Technical impactpartial
Scored2026-08-18

Timeline

  1. 2026-08-17Published by the CNA20:13 UTC
  2. 2026-08-18CISA SSVC decision recorded1 day after publication
  3. 2026-09-04GitHub advisory published (GHSA-8737-qx52-hjff)18 days after publication

The timeline shows what already happened. To be told when this CVE changes next, watch it from the API.

Exploit and advisory records

GitHub advisory GHSA-8737-qx52-hjff, affected packages:

PackageVulnerable versionsFixed in
PyPI vllmbefore 0.26.00.26.0

Affected products

Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.

ProductVulnerable versionsFixed in
vllm vllmbefore 0.26.0fixed in 0.26.00.26.0

Products and versions as NVD and the vendor that published the CVE list them.

References

Get more CVE data from the API.

Free without a key or signup. Pro adds monitoring and higher limits: pricing.

Sources