GithubHelp home page GithubHelp logo

nineis7 / tvm-gpt Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 0.0 166.46 MB

Python 20.90% Shell 0.44% CMake 10.05% Makefile 28.82% Java 0.18% C++ 23.34% RenderScript 0.01% C 15.25% Objective-C 0.03% Objective-C++ 0.08% Rust 0.34% Groovy 0.29% Jinja 0.04% Batchfile 0.01% Go 0.10% Cython 0.03% Cuda 0.05% Assembly 0.02% HTML 0.01% JavaScript 0.02%

tvm-gpt's Introduction

gpt-frontend

Reference

参考bert

nanoGPT video course

Build

git clone --recursive http://github.com/nineis7/gpt-frontend.git

采用http协议,防止连接不稳定

build with docker:

参见[TVM docker cuda环境配置最新方案.md]一文

build tvm

cd gpt-frontend/tvm
mkdir build
cp cmake/config.cmake build/
cd build
cmake ..
make -j8

build with PAPI (cmake has been updated to 3.24.1 in cmake_source.sh)

PAPI使用参见[PAPI profiling.md]一文

# Method 1:在docker/install中将ubuntu_install_papi.sh添加进build.sh中
# 需要修改export PAPI_CUDA_ROOT=/usr/local/cuda 为cuda->该文件夹下cuda版本号

# Method 2:手动安装
git clone --branch papi-6-0-0-1-t https://bitbucket.org/icl/papi.git
cd papi/src
export PAPI_CUDA_ROOT=/usr/local/cuda版本号(需自行查看)
# export PAPI_ROCM_ROOT=/opt/rocm 可以不安装
./configure --with-components="cuda"
make && make install

安装后重新cmake|make来build tvm

目前进度:

  • week1:实现driver_gpt.py 将gpt在tvm中运行并优化,测试性能作为benchmark
  • week2-3:搭建WSL2+docker+cuda环境,实现tvm在WSL2中运行
  • week4:实现gpt在WSL2中运行并优化,测试性能作为benchmark(包括fp32->16,fused mha)
  • week5;PAPI编译安装,进行基于llvm与cuda的gpt model性能测试,结果见artifacts/PAPI_profiling

tvm-gpt's People

Contributors

nineis7 avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.