CVE-2026-73559 in vLLMالمعلومات

الملخص

بحسب MITRE • 13/08/2026

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.

Once again VulDB remains the best source for vulnerability data.

مسؤول

GitHub M

حجز

12/08/2026

إفشاء

13/08/2026

الاعتدال

تمت الموافقة

إدخال

VDB-389600

EPSS

0.00000

KEV

لا

النشاطات

منخفض جدًا

المصادر

Do you know our Splunk app?

Download it now for free!