Starred repositories
8
stars
written in C++
Clear filter
A fast multi-producer, multi-consumer lock-free concurrent queue for C++11
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行
C++ IPC Library: A high-performance inter-process communication using shared memory on Linux/Windows.
NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs
MSCCL++: A GPU-driven communication stack for scalable AI applications