Pinned Loading

1. gdr-copy gdr-copy Public

   基于ibverbs使用GPUDirect RDMA技术实现的H2D/D2H传输

   C++

2. inter-node-communication-test inter-node-communication-test Public

   H2D通信和节点间NCCL集合通信影响，与带宽控流尝试

   Cuda

3. cuda-exercises cuda-exercises Public

   CUDA编程笔记和LeetGPU的算子实践

   Cuda

4. pokemon-text-battle pokemon-text-battle Public

   和LLM进行第九代宝可梦文字对战。You can play pokemon gen9randombattle using the command line vs AI.

   TypeScript 1 1

5. unified-cache-management unified-cache-management Public

   Forked from ModelEngine-Group/unified-cache-management

   Persist and reuse KV Cache to speedup your LLM.

   Python

6. ModelEngine-Group/fit-framework ModelEngine-Group/fit-framework Public

   FIT: 企业级AI开发框架，提供多语言函数引擎（FIT）、流式编排引擎（WaterFlow）及Java生态的LangChain替代方案（FEL）。原生/Spring双模运行，支持插件热插拔与智能聚散部署，无缝统一大模型与业务系统。

   Java 2.1k 333