LLMHao's repositories
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
onnx
Open Neural Network Exchange
onnx-modifier
A tool to modify onnx models in a visualization fashion, based on Netron and flask.
copilot-docs
Documentation for GitHub Copilot
RepVGG
RepVGG: Making VGG-style ConvNets Great Again
apollo
An open autonomous driving platform
PaddleSlim
PaddleSlim is an open-source library for deep model compression and architecture search.
netron
Visualizer for neural network, deep learning, and machine learning models
AMDMIGraphX
AMD's graph optimization engine.
tensorflow-onnx
Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
apriltag
AprilTag is a visual fiducial system popular for robotics research.
CUDA_CCL
A Connected Component Labelling algorithm implemented in CUDA
Megatron-LM
Ongoing research training transformer language models at scale, including: BERT & GPT-2
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
speechbrain
A PyTorch-based Speech Toolkit
gloo
Collective communications library with various primitives for multi-machine training.
ekho
Chinese text-to-speech engine
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
gtn
Automatic differentiation with weighted finite-state transducers.
cub
Cooperative primitives for CUDA C++.
TurboTransformers
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
espnet
End-to-End Speech Processing Toolkit
k2
FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar
effective_transformer
Running BERT without Padding
g2pM
A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset