pytorch / pytorch

Star

Open

Implement torch.max for float16 and bfloat16 on CPU and CUDA

16

kurtamohler commented Jan 20, 2021

🚀 Feature

Add support for torch.max with:

CUDA bfloat16
CPU float16 and bfloat16

Motivation

Currently, torch.max has support for CUDA float16:

>>> torch.rand(10, dtype=torch.float16, device='cuda').max()
tensor(0.8530, device='cuda:0', dtype=torch.float16)

But all three other combinations of CPU/CUDA and float16/bfloat16 are not supported:

>>> torch.ra

torch.eye(d) is slow and hogs cpu for d >= 182

4

Open

Tensor with read only memory mapped numpy array causes seg fault.

4

Find more good first issues →

chenyuntc / pytorch-book

Star

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

deep-learning jupyter-notebook nn pytorch autograd caption gan image-classification tensorboard tensor neural-style visdom pytorch-tutorials pytorch-tutorials-cn charrnn neuraltalk

Updated Dec 22, 2020
Jupyter Notebook

apache / tvm

Star

Open deep learning compiler stack for cpu, gpu and specialized accelerators

javascript machine-learning performance deep-learning metal compiler gpu vulkan opencl tensor spirv rocm tvm

Updated Feb 6, 2021
Python

cupy / cupy

Star

A NumPy-compatible array library accelerated by CUDA

python gpu numpy cuda cublas scipy tensor cudnn cupy cusolver nccl curand cusparse nvrtc cutensor nvtx

Updated Feb 6, 2021
Python

guoguibing / librec

Star

LibRec: A Leading Java Library for Recommender Systems, see

java matrix collaborative-filtering matrix-factorization systems sparse recommender tensor-factorization collaborative tensor factorization filtering recommender-systems recommendation-algorithms probabilistic-graphical-models

Updated Oct 22, 2020
Java

arogozhnikov / einops

Star

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

deep-learning chainer tensorflow numpy keras pytorch tensor gluon cupy jax

Updated Jan 9, 2021
Python

mars-project / mars

Star

Open

Implements {DataFrame,Series}.empty

7

wjsi commented Dec 25, 2020

Implements {DataFrame,Series}.empty

Support `Series.between`

Open

Support {DataFrame,Series}.add_prefix

Find more good first issues →

danielhanchen / hyperlearn

Star

50% faster, 50% less RAM Machine Learning. Numba rewritten Sklearn. SVD, NNMF, PCA, LinearReg, RidgeReg, Randomized, Truncated SVD/PCA, CSR Matrices all 50+% faster

python data-science machine-learning statistics research deep-learning neural-network gpu optimization scikit-learn pytorch econometrics data-analysis tensor regression-models statsmodels

Updated Sep 18, 2020
Jupyter Notebook

tensorly / tensorly

Star

TensorLy: Tensor Learning in Python.

python machine-learning mxnet tensorflow numpy pytorch decomposition tensor-factorization tensor tensor-algebra tensorly tensor-learning tensor-decomposition cupy tensor-regressions tensor-methods jax

Updated Feb 3, 2021
Python

tensor-compiler / taco

Star

The Tensor Algebra Compiler (taco) computes sparse tensor expressions on CPUs and GPUs

library code-generator linear-algebra sparse tensor tensor-algebra tensor-algebra-compiler

Updated Feb 6, 2021
C++

egison / egison

Star

Open

Add missing test for standard libraries

momohatt commented Aug 12, 2020

Tests for following standard libraries seem to be missing. Although some libraries might be difficult to test (such as random.egi or io.egi), it'd be nice to have some tests that make sure all the functions in these libraries can be (at least) executed without dynamic errors.

mratsim / Arraymancer

Star

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

Updated Jan 20, 2021
Nim

andrewssobral / lrslibrary

Star

Low-Rank and Sparse Tools for Background Modeling and Subtraction in Videos

matlab matrix matrix-factorization tensor lin rpca matrix-completion tensor-decomposition subspace-tracking subspace-learning zhou

Updated Apr 23, 2020
MATLAB

zdevito / ATen

Star

ATen: A TENsor library for C++11

pytorch tensor torch7

Updated Nov 20, 2019
C++

hfp / libxsmm

Star

Library for specialized dense and sparse matrix operations, and deep learning primitives.

machine-learning fortran vector matrix intel avx sse jit simd matrix-multiplication sparse blas convolution avx2 amx tensor avx512 transpose bfloat16

Updated Feb 6, 2021
C

OAID / AutoKernel

Star

AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。

reinforcement-learning deep-learning tensorflow optimization pytorch tengine halide tensor auto autosearch tvm

Updated Dec 22, 2020
C++

merrymercy / awesome-tensor-compilers

Star

A list of awesome compiler projects and papers for tensor computation and deep learning.

programming-language machine-learning deep-learning compiler high-performance-computing code-generation tensor

Updated Feb 4, 2021

dgasmith / opt_einsum

Star

⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.

python performance gpu-acceleration tensor contraction

Updated Dec 29, 2020
Python

dmlc / dlpack

Star

RFC for common in-memory tensor structure and operator interface for deep learning system

deep-learning operator tensor

Updated Feb 6, 2021
C

DiffSharp / DiffSharp

Star

DiffSharp: Differentiable Functional Programming

machine-learning deep-learning neural-network dotnet gpu tensor autodiff

Updated Jan 20, 2021
F#

NiuTrans / NiuTensor

Star

NiuTensor is an open-source toolkit developed by a joint team from NLP Lab. at Northeastern University and the NiuTrans Team. It provides tensor utilities to create and train neural networks.

machine-learning deep-learning artificial-neural-networks tensor