q yao's repositories
mmdetection-to-tensorrt
convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.
torch2trt_dynamic
A pytorch to tensorrt convert with dynamic shape support
amirstan_plugin
Useful tensorrt plugin. For pytorch and mmdetection model conversion.
TorchMPSCustomOpsDemo
A demo about how to add custom MPS ops in PyTorch.
coremltools
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
cutlass
CUDA Templates for Linear Algebra Subroutines
DeepEP
DeepEP: an efficient expert-parallel communication library
effective-debugging-zh
effective debugging 中文翻译
FasterTransformer
Transformer related optimization, including BERT, GPT
grimoire.github.io
My github pages website
MegEngine
MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架
MinerU
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。
mmdetection
OpenMMLab Detection Toolbox and Benchmark
mmrotate
OpenMMLab Rotated Object Detection Toolbox and Benchmark
mmyolo
OpenMMLab YOLO series toolbox and benchmark
oneDNN
oneAPI Deep Neural Network Library (oneDNN)
onnx
Open standard for machine learning interoperability
onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
ppl.nn
A primitive library for neural network
ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
pybind11
Seamless operability between C++11 and Python
SimpleNES
An NES emulator in C++
the-art-of-debugging
The Art of Debugging
triton
Development repository for the Triton language and compiler
Triton-distributed
Distributed Triton for Parallel Systems