Pinned Loading

1. mini-infer mini-infer Public

   LLM inference engine from scratch — paged KV cache, continuous batching, chunked prefill, prefix caching, speculative decoding, CUDA graph, tensor parallelism, MoE expert parallelism, OpenAI-compat…

   Python 128 6

2. PMPP-Learning PMPP-Learning Public

   Programming Massively Parallel Processors (4th Ed.) 大规模并行处理器程序设计、学习笔记、练习题解答与 CUDA 实现

   C++ 96 10

3. UESTC-NET UESTC-NET Public

   UESTC 校园网自动认证登录（牛马专用版）

   Python 5

4. CUDA-Practice CUDA-Practice Public

   CUDA编程练习项目-Hands-on CUDA kernels and performance optimization, covering GEMM, FlashAttention, Tensor Cores, CUTLASS, quantization, KV cache, NCCL, and profiling.

   Cuda 75 6

5. Campus_Spring_boot Campus_Spring_boot Public

   A Spring Boot-based campus item sharing platform that enables students to share, exchange items. Features: user auth, item management, real-time chat | 基于Spring Boot的校园物品共享平台

   Java 2

6. CampusShare-AI CampusShare-AI Public

   🎓 智能校园物品共享平台 | Smart Campus Item Sharing Platform powered by Google Gemini AI

   Kotlin 2