w1d2s

w1d2s's Stars

• parallel101/course

  高性能并行编程与优化 - 课件

  Language:C++3.8k546

• facebookresearch/xformers

  Hackable and optimized Transformers building blocks, supporting a composable construction.

  Language:Python8.9k634

• Oneflow-Inc/oneflow

  OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

  Language:C++6.5k726

• Linux-cpp-lisp/opt_einsum_fx

  Einsum optimization using opt_einsum and PyTorch FX graph rewriting

  Language:Python195

• cameron314/concurrentqueue

  A fast multi-producer, multi-consumer lock-free concurrent queue for C++11

  Language:C++10.4k1.7k

• k2-fsa/k2

  FSA/FST algorithms, differentiable, with PyTorch compatibility.

  Language:Cuda1.1k217

• jiaaro/pydub

  Manipulate audio with a simple and easy high level interface

  Language:Python9.1k1.1k

• wenet-e2e/WenetSpeech

  A 10000+ hours dataset for Chinese speech recognition

  Language:Shell51149

• hanickadot/compile-time-regular-expressions

  Compile Time Regular Expression in C++

  Language:C++3.4k188

• athena-team/athena-decoder

  Language:Python7526

• gmagogsfm/TorchScriptStudy

  Studying TorchScript features

  Language:Python1

• microsoft/qlib

  Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.

  Language:Python15.9k2.7k

• xboot/libonnx

  A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

  Language:C592108

• SpeechColab/GigaSpeech

  Large, modern dataset for speech recognition

  Language:Shell65362

• max0x7ba/atomic_queue

  C++14 lock-free queue.

  Language:C++1.6k183

• nvbn/thefuck

  Magnificent app which corrects your previous console command.

  Language:Python88.5k3.5k

• kimiyoung/transformer-xl

  Language:Python3.6k762

• RoyJames/room-impulse-responses

  A list of publicly available room impulse response datasets and scripts to download them.

  Language:Shell42535

• electronicarts/EASTL

  EASTL stands for Electronic Arts Standard Template Library. It is an extensive and robust implementation that has an emphasis on high performance.

  Language:C++8.4k955

• facebook/folly

  An open-source C++ library developed and used at Facebook.

  Language:C++28.6k5.6k

• apache/brpc

  brpc is an Industrial-grade RPC framework using C++ Language, which is often used in high performance system such as Search, Storage, Machine learning, Advertisement, Recommendation etc. "brpc" means "better RPC".

  Language:C++16.7k4k

• kweonwooj/papers

  summary of ML papers I've read

  31934

• OpenNMT/OpenNMT-py

  Open Source Neural Machine Translation and (Large) Language Models in PyTorch

  Language:Python6.8k2.2k

• harvardnlp/seq2seq-attn

  Sequence-to-sequence model with LSTM encoder/decoders and attention

  Language:Lua1.3k280

• DeepVAC/libdeepvac

  Use PyTorch model in C++ project

  Language:C++13523

• pytorch/TensorRT

  PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

  Language:Python2.6k355

• Tencent/Forward

  A library for high performance deep learning inference on NVIDIA GPUs.

  Language:C++54967

• knik0/faac

  Freeware Advanced Audio Coder faac mirror

  Language:C18460

• skarupke/flat_hash_map

  A very fast hashtable

  Language:C++1.7k187

• alibaba/MNN

  MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

  Language:C++8.9k1.7k