Pinned Loading

1. PowerInfer PowerInfer Public

   High-speed Large Language Model Serving for Local Deployment

   C++ 8.3k 443

2. OS-Course-Lab OS-Course-Lab Public

   本仓库包含上海交通大学IPADS实验室设计的操作系统课程系列实验。

   C 409 120

3. ServerlessBench ServerlessBench Public

   A benchmark suite for serverless computing

   C++ 227 38

4. PhoenixOS PhoenixOS Public

   Fast OS-level support for GPU checkpoint and restore

   C++ 226 24

5. reef reef Public

   REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU scheduling.

   Cuda 96 12

6. SmallThinker SmallThinker Public

   28