bjmsong Goto Github PK

bjmsong.github.io

caffe

Caffe: a fast open framework for deep learning.

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

cuda_programming

Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch

cudalibrarysamples

CUDA Library Samples

cutlass

CUDA Templates for Linear Algebra Subroutines

deeplearningfromscratch

《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​

deepspeedexamples

Example models using DeepSpeed

dlrm

An implementation of a deep learning recommendation model (DLRM)

fastapi-course

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

flash-attention

Fast and memory-efficient exact attention

flash_attention_inference

Performance of the C++ interface of flash attention, flash attention v2 and self quantized decoding attention in large language model (LLM) inference scenarios.

hands-on-gemm

Matrix Multiplication Optimization on GPU/CPU

how-to-optimize-gemm

row-major matmul optimization

hw05

inference

Reference implementations of MLPerf™ inference benchmarks

inference_results_v3.1

This repository contains the results and code for the MLPerf™ Inference v3.1 benchmark.

inference_results_v4.0

This repository contains the results and code for the MLPerf™ Inference v4.0 benchmark.

libflash_attn

Standalone Flash Attention v2 kernel without libtorch dependency

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

llama2.c

Inference Llama 2 in one file of pure C

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

nanogpt

The simplest, fastest repository for training/finetuning medium-sized GPTs.

nlp-tutorial

Natural Language Processing Tutorial for Deep Learning Researchers

online-softmax

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

ostep-projects

Projects for an undergraduate OS course

ppl.cv

ppl.cv is a high-performance image processing library of openPPL supporting various platforms.

ppl.llm.kernel.cuda

ppl.nn

A primitive library for neural network