vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds (vllm-project vllm)

CVE-2026-71486
MEDIUM 4.3

At a glance

Source
NVD
EPSS
EPSS 0.37 % · percentile 31 ()
State
PUBLISHED
Published
Updated
Assigner
GitHub_M
NVD status
Analyzed

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.

Weaknesses (CWE)

  • CWE-400 — Uncontrolled Resource Consumption
  • CWE-770 — Allocation of Resources Without Limits or Throttling

References

Scores

VersionScoreVectorScored by
CVSS 3.1MEDIUM 4.3CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:LGitHub_M
CVSS 3.1MEDIUM 4.3CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:LNVD · security-advisories@github.com (Secondary)

Advisories

European references

Affected configurations (NVD CPE)

Affected products

ProductVersions
vllm-project · vllmaffected < 0.26.0

Sources

SourceLicence
CVE List (CVEProject cvelistV5)CVE Program Terms of Use
EPSS (FIRST.org)FIRST — attribution requested
ENISA EUVDENISA — reproduction authorised, source acknowledged
NVD (NIST) via fkie-cad/nvd-json-data-feedsPublic domain — this product uses data from the NVD API but is not endorsed or certified by the NVD