CVE-2026-73559: Vllm

Medium severity, CVSS 6.5. EPSS: 0.6% chance of exploitation in the next 30 days.

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 products

• Vllm Vllm: from 0.19.0, before 0.26.0 (fixed in 0.26.0)

Published 2026-08-13. Last modified 2026-09-28.