fasth icon indicating copy to clipboard operation
fasth copied to clipboard

verified publisher icon AlexanderMath
→

Metadata

Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.

Results 3 fasth issues
Sort by recently updated
recently updated
newest added

OOM on large matrices

I am trying to do SVD on sparse data. My U,V matrices are of size 30000x50. When I try fasth for making those orthogonal, it tries to allocate 30000x30000 matrix.....

renjithravindran avatar renjithravindran

A problem

When I run the test_case.py locally, I will report an error: Traceback (most recent call last): File "test_case.py", line 37, in from fasth_wrapper import * File "E:\code\SVDH\fasth-master\fasth_wrapper.py", line 38, in...

HaitaoZhang-ZHT avatar HaitaoZhang-ZHT

Bump torch from 1.3.1 to 2.2.0

Bumps [torch](https://github.com/pytorch/pytorch) from 1.3.1 to 2.2.0. Release notes Sourced from torch's releases. PyTorch 2.2: FlashAttention-v2, AOTInductor PyTorch 2.2 Release Notes Highlights Backwards Incompatible Changes Deprecations New Features Improvements Bug fixes...

dependabot[bot] avatar dependabot[bot]

dependencies

← Metadata

63
Stars
9
Forks
Watchers

Owner

verified publisher icon AlexanderMath

Metadata

Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.

Back