HJzhang-sjtu

HJzhang-sjtu's Stars

• rigtorp/c2clat

  A tool to measure CPU core to core latency

  Language:C++12622

• microsoft/T-MAC

  Low-bit LLM inference on CPU with lookup table

  Language:C++37830

• Sunny-Island/winograd-onlyJava

  Language:C323

• microsoft/BitBLAS

  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

  Language:Python28728

• pigirons/cpufp

  A CPU tool for benchmarking the peak of floating points

  Language:Assembly462120

• connorimes/poster-copper-icac-2019

  CoPPer: Soft Real-time Application Performance Using Hardware Power Capping

  Language:TeX1

• ThijsRay/coppers

  Coppers is a custom test harnass for Rust that measures the energy usage of your test suite.

  Language:Rust1807

• yiminga/RLFreq

  Online Power Management for Multi-Cores: A Reinforcement Learning Based Approach

  Language:Python2

• SJTU-IPADS/PowerInfer

  High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

  Language:C++7.8k401

• OpenPPL/ppl.nn.llm

  14018

• e-wxy/AICS-Coursework

  A record of coursework in AI Computing Systems, mainly focusing on high performance computing development for MLU.

  Language:C++142

• LeiWang1999/AICS-Course

  《智能计算系统 AI Computing Systems》习题答案、实验答案、课程笔记

  Language:C++17727

• obilaniu/libpfc

  A small library and kernel module for easy access to x86 performance monitor counters under Linux.

  Language:C8912

• intel/pcm

  Intel® Performance Counter Monitor (Intel® PCM)

  Language:C++2.7k465

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++8k883

• hpc-cool/swPerfModeling

  Language:C3

• OpenPPL/ppl.llm.kernel.cuda

  Language:C++13324

• fpgaminer/GPTQ-triton

  GPTQ inference Triton kernel

  Language:Jupyter Notebook27121

• Tencent/TNN

  TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.

  Language:C++4.4k764

• triton-lang/triton

  Development repository for the Triton language and compiler

  Language:C++12.4k1.5k

• Bruce-Lee-LY/cuda_hgemm

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

  Language:Cuda25561

• IST-DASLab/gptq

  Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

  Language:Python1.9k150

• spcl/LogGOPSim

  A LogGOPS (LogP, LogGP, LogGPS) Simulator and Simulation Framework

  Language:C106

• simgrid/simgrid

  MIRROR of the SimGrid framework, for the simulation of distributed applications (Clouds, HPC, Grids, IoT and others). Most of the dev occurs on FramaGit.

  Language:C++16591

• siboehm/SGEMM_CUDA

  Fast CUDA matrix multiplication from scratch

  Language:Cuda39652

• geekpiehpc/wiki

  Language:Python32

• OpenPPL/CuAssembler

  An unofficial cuda assembler, for all generations of SASS, hopefully ：）

  Language:Python7310

• yzhaiustc/Optimizing-SGEMM-on-NVIDIA-Turing-GPUs

  Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

  Language:Cuda26543

• b4be1/packet-client-linux

  Optitrack Packet Client for Linux (NatNet 2.5-3.0)

  Language:C++43

• parallel101/course

  高性能并行编程与优化 - 课件

  Language:C++3.6k531