Pinned Repositories
convnet-benchmark-py
PyTorch convnet performance benchmark
op_bench-py
performance benchmark for pytorch operators
pytorch_nersc_wheel
PyTorch wheel installation file with performance optimization on CPU
pytorch_profiler_parser
parser script to process pytorch autograd profiler result, convert json file to excel.
mingfeima's Repositories
mingfeima/op_bench-py
performance benchmark for pytorch operators
mingfeima/convnet-benchmark-py
PyTorch convnet performance benchmark
mingfeima/pssp
PyTorch implementations of protein secondary structure prediction.
mingfeima/detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
mingfeima/pytorch_block_sparse
Fast Block Sparse Matrices for Pytorch
mingfeima/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
mingfeima/ideep
Intel® Optimization for Chainer*, a Chainer module providing numpy like API and DNN acceleration using MKL-DNN.
mingfeima/inference
Reference implementations of inference benchmarks
mingfeima/lite-transformer
[ICLR 2020] Lite Transformer with Long-Short Range Attention
mingfeima/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
mingfeima/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
mingfeima/serve
Model Serving on PyTorch
mingfeima/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
mingfeima/whisper.cpp
Port of OpenAI's Whisper model in C/C++
mingfeima/bench_sdpa
smoke test and benchmark for sdpa
mingfeima/BitNet
Official inference framework for 1-bit LLMs
mingfeima/ChatRWKV
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
mingfeima/cpuinfo
CPU INFOrmation library (x86/x86-64/ARM/ARM64, Linux/Windows/Android/macOS/iOS)
mingfeima/espnet
End-to-End Speech Processing Toolkit
mingfeima/extension-cpp
C++ extensions in PyTorch
mingfeima/flashinfer
FlashInfer: Kernel Library for LLM Serving
mingfeima/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
mingfeima/Informer2020
The GitHub repository for the paper "Informer" accepted by AAAI 2021.
mingfeima/llama.cpp
Port of Facebook's LLaMA model in C/C++
mingfeima/llm.c
LLM training in simple, raw C/CUDA
mingfeima/pytorch_geometric
Graph Neural Network Library for PyTorch
mingfeima/sglang
SGLang is a fast serving framework for large language models and vision language models.
mingfeima/SqueezeLLM
SqueezeLLM: Dense-and-Sparse Quantization
mingfeima/tutorials
PyTorch tutorials.
mingfeima/vision
Datasets, Transforms and Models specific to Computer Vision