CVE-2026-73559
CVE-2026-73559 · vLLM: Completion prompt lists fan out into unbounded engine requests
Cette page présente des faits issus de sources publiques. Consultez l’avis original avant toute mise à jour.
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 · Moyenne · EPSS 0,6% · Correctif disponible
- Publication
- Mise à jour
Pile logicielle: python
Produits et versions concernés
Sources originales
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
- https://github.com/vllm-project/vllm/pull/47845
- https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0
- https://nvd.nist.gov/vuln/detail/CVE-2026-73559