通义千问VLLM推理部署DEMO

Archived implementation of BLAS using the SYCL open standard. See oneMath for a replacement.

GPGPU-Sim provides a detailed simulation model of contemporary NVIDIA GPUs running CUDA and/or OpenCL workloads. It includes support for features such as TensorCores and CUDA Dynamic Parallelism as…

We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstra…

C++ Tip Of The Week

A Easy-to-understand TensorOp Matmul Tutorial

Tile primitives for speedy kernels

Random for modern C++ with convenient API

C++20 μ(micro)/Unit Testing Framework

A minimal GPU design in Verilog to learn how GPUs work from the ground up

the resources about the application based on LLM with RAG pattern

一个基于langchain实现RAG的简单示例

A comprehensive guide to building RAG-based LLM applications for production.

A simple high performance CUDA GEMM implementation.

📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

A tool for bandwidth measurements on NVIDIA GPUs.

Benchmark code for the "Online normalizer calculation for softmax" paper

collection of benchmarks to measure basic GPU capabilities

C++ project template with unit-tests, documentation, ci-testing and workflows.

An extension library of WMMA API (Tensor Core API)

A collection of out-of-tree Clang plugins for teaching and learning

Rich is a Python library for rich text and beautiful formatting in the terminal.

Matrix Multiply-Accumulate with CUDA and WMMA( Tensor Core)

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

llvm-tutorial文档，翻译以及代码仓库

图解计算机网络、操作系统、计算机组成、数据库，共 1000 张图 + 50 万字，破除晦涩难懂的计算机基础知识，让天下没有难懂的八股文！🚀 在线阅读：https://xiaolincoding.com