p PatchFirst

CVE-2026-73559

CVE-2026-73559 · vLLM: Completion prompt lists fan out into unbounded engine requests

Esta página presenta datos de fuentes públicas de vulnerabilidades. Consulta el aviso original antes de actualizar.

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.

CVSS 6.5 · Media · EPSS 0,6% · Corrección disponible

Publicación
Actualización

Pila tecnológica: python

Productos y versiones afectados

  • vllm

    Versiones
    • >= 0.19.0, < 0.26.0: Afectada

    Sin corrección publicada

  • vllm PyPI

    Versiones
    • 0.19.0
    • 0.19.1
    • 0.20.0
    • 0.20.1
    • 0.20.2
    • 0.21.0
    • 0.22.0
    • 0.22.1
    • 0.23.0
    • 0.24.0
    • 0.25.0
    • 0.25.1
    Intervalos de versiones afectados
    • ECOSYSTEM: ≥ 0.19.0, < 0.26.0

    Actualiza a 0.26.0

Fuentes originales

Comprueba tu servidor →