|
About the performance category
|
|
0
|
57
|
January 22, 2021
|
|
CUDA loops case study: code generation vs templates
|
|
3
|
292
|
September 8, 2021
|
|
Multiple workers for single batch
|
|
2
|
107
|
July 14, 2021
|
|
Optimizing contiguous() for the case where the Tensor is_contiguous()?
|
|
6
|
332
|
May 24, 2021
|
|
Making Transformer inference faster on GPUs
|
|
0
|
339
|
April 2, 2021
|
|
Converting weights flat buffer
|
|
0
|
78
|
March 25, 2021
|
|
Why `torch::jit::pop` (and sometimes push) is worse for performance than direct `std::vector` access
|
|
0
|
176
|
March 17, 2021
|
|
Pytorch Benchmarks issues with general usability and issues with individual benchmarks
|
|
2
|
223
|
March 12, 2021
|
|
GPU Overheads and Fused Strassen
|
|
0
|
144
|
February 13, 2021
|
|
Comparing the performance of 0.4.1 and master
|
|
0
|
656
|
February 9, 2021
|
|
Overhead in `nn.Module` causing massive slowdowns compared to raw CuBLAS or Torchscript
|
|
0
|
452
|
January 28, 2021
|
|
Dispatcher Performance and Inlining: a Report on Two Days Spent on Dispatcher Performance
|
|
1
|
257
|
January 28, 2021
|
|
We shouldn't feel bad about passing `Tensor` by reference
|
|
0
|
178
|
January 25, 2021
|
