由于 trendforge.devlive.top 访问受限,请切换到 trendforge.devlive.org 域名
llm-serving
话题找到数量
NVIDIA/TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
skypilot-org/skypilot
在任何AI基础设施上运行、管理和扩展AI工作负载。使用统一系统访问和管理所有AI计算资源(Kubernetes、17+云平台或本地部署)。