CVE-2026-73559

Name of the Vulnerable Software and Affected Versions vLLM versions 0.19.0 through 0.25.0

Description The /v1/completions endpoint accepts an unbounded prompt field within the CompletionRequest. The prompt to seq() and OnlineRenderer.preprocess completion() functions expand every element of the input, while the serving logic creates an engine generator and response slot for each prompt. This allows an authenticated API client to exhaust CPU, memory, asynchronous scheduling capacity, engine request slots, and response buffering using a single request.

Recommendations Update to version 0.26.0.