Skip to content
LLMHigh

CVE-2026-73559: vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1…

Occurred
Aug 13, 2026
Published
Aug 13, 2026
Source
NVD CVE

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.

Tags

  • CVE
  • CVE-2026-73559
  • cvss:MEDIUM

Classification

Category confidence: 95%
Severity confidence: 90%

Rationale: CVE describes a denial-of-service vulnerability in vLLM LLM serving engine allowing resource exhaustion via unbounded prompt lists.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source