mingfeima

Ma Mingfei's repositories

op_bench-py

performance benchmark for pytorch operators

Language:Python800

convnet-benchmark-py

PyTorch convnet performance benchmark

Language:Python600

pssp

PyTorch implementations of protein secondary structure prediction.

Language:Python4 10

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

Language:PythonApache-2.0200

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch

NOASSERTION200

dlrm

An implementation of a deep learning recommendation model (DLRM)

Language:PythonMIT1 10

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Language:PythonMIT1 20

gen-efficientnet-pytorch

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

Language:PythonApache-2.01 10

ideep

Intel® Optimization for Chainer*, a Chainer module providing numpy like API and DNN acceleration using MKL-DNN.

Language:C++MIT1 10

inference

Reference implementations of inference benchmarks

Language:PythonApache-2.0100

lite-transformer

[ICLR 2020] Lite Transformer with Long-Short Range Attention

NOASSERTION100

oneDNN

oneAPI Deep Neural Network Library (oneDNN)

Language:C++Apache-2.01 10

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Language:C++NOASSERTION1 20

serve

Model Serving on PyTorch

Language:JavaApache-2.01 10

tacotron2

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Language:Jupyter NotebookBSD-3-Clause100

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Apache-2.0100

whisper.cpp

Port of OpenAI's Whisper model in C/C++

MIT100

bench_sdpa

smoke test and benchmark for sdpa

Language:Python000

ChatRWKV

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Apache-2.0000

cpuinfo

CPU INFOrmation library (x86/x86-64/ARM/ARM64, Linux/Windows/Android/macOS/iOS)

Language:CBSD-2-Clause000

espnet

End-to-End Speech Processing Toolkit

Language:PythonApache-2.0010

extension-cpp

C++ extensions in PyTorch

000

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonBSD-3-Clause000

Informer2020

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

Apache-2.0000

llama.cpp

Port of Facebook's LLaMA model in C/C++

Language:C++MIT000

llm.c

LLM training in simple, raw C/CUDA

MIT000

pytorch_geometric

Graph Neural Network Library for PyTorch

MIT000

SqueezeLLM

SqueezeLLM: Dense-and-Sparse Quantization

MIT000

tutorials

PyTorch tutorials.

Language:PythonBSD-3-Clause000

vision

Datasets, Transforms and Models specific to Computer Vision

Language:PythonBSD-3-Clause010