Pinned Loading

1. LeetGPU-Guidebook LeetGPU-Guidebook Public

   一步步通关GPU编程

   Cuda 50 7

2. vllm-kivi vllm-kivi Public

   Production-ready 2/4-bit KV Cache quantization for vLLM via Triton; 70% VRAM saving & 1.8x speedup

   Python 2

3. cpp-performance-lab cpp-performance-lab Public

   C++ microbenchmark lab for cache, memory, ILP, synchronization, queue, and allocator experiments

   C++ 1

4. qlib-gpu-model qlib-gpu-model Public

   GPU-first quant deep learning starter built with PyTorch and Qlib-style data pipelines

   Python 1