A AegiFlow
MEDIUMCVSS 6.5EPSS 0.4%

CVE-2026-73559

CVE-2026-73559 updated by NVD

Published
2026-08-13
Modified
2026-09-11
EPSS percentile
32%
Sources
github-advisory, nvd

Summary

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.

Affected packages

EcosystemPackageAffected versionsFixed versions
PyPIvllm0.26.0

Remediation: Upgrade to 0.26.0 or later.

References

Includes data from the GitHub Advisory Database, licensed under CC-BY 4.0.

Includes data from the National Vulnerability Database (NIST). NVD data is in the public domain; this page is not endorsed by NIST.

CVE® is a registered trademark of The MITRE Corporation. CVE content reproduced under the CVE Terms of Use; copyright designation © MITRE.

EPSS scores provided by the FIRST.org Exploit Prediction Scoring System.