zhaohb Goto Github PK

gpu-manager

grpc_demo

hip

HIP: C++ Heterogeneous-Compute Interface for Portability

how-to-optimize-gemm

how_to_optimize_in_gpu

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

hpc-learning

hpc-learning

inferencehelper

Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, ncnn, MNN, SNPE, Arm NN, NNAbla

interview_internal_reference

2019年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

jittor

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

k8s-hostdev-plugin

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

kuiperinfer

带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

lihang-code

《统计学习方法》的代码实现

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

micronet

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

mig-parted

MIG Partition Editor for NVIDIA GPUs

mimalloc

mimalloc is a compact general purpose allocator with excellent performance.

min-tfs-client

A lightweight python gRPC client to communicate with TensorFlow Serving

minpy

NumPy interface with mixed backend execution

mkl-dnn

Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)

ml-performance-prediction

Code that accompanies the paper "Predicting the Computational Cost of Deep Learning Models"

ml-workspace

🛠 All-in-one web-based IDE specialized for machine learning and data science.

mmdeploy

MMDeploy is an open-source deep learning model deployment toolset

mmdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

model_server

A scalable inference server for models optimized with OpenVINO™

model_split

A simple CNN network is implemented on FPGA, but the resource of FPGA is not fully used, only to achieve the purpose of calculation

models

Model Zoo for Intel® Architecture: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors