CVE-2026-73559
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.
Słabość
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.
Źródła
- https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
- https://github.com/vllm-project/vllm/pull/47845
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
- https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
Znajdź błąd, zanim zrobi to atakujący.
Zaloguj się przez GitHub i uruchom pierwszy audyt w niecałą minutę. Plan darmowy nie wymaga karty kredytowej.