|
About the autograd category
|
|
0
|
4097
|
May 13, 2017
|
|
I built a Python library for cost-aware activation checkpoint placement
|
|
0
|
32
|
August 31, 2026
|
|
Building a PyTorch curriculum that teaches math through code, not as a prerequisite
|
|
2
|
157
|
August 24, 2026
|
|
Does autograd differentiate with respect to the linspace arguments
|
|
2
|
117
|
August 3, 2026
|
|
Is it safe to reuse the same PyTorch loss module across multiple environments in a single training iteration?
|
|
2
|
143
|
July 6, 2026
|
|
Truncating part of a computational graph
|
|
1
|
101
|
June 16, 2026
|
|
Continuous CPU RAM growth during LSTM training with cuDNN enabled (PyTorch 2.7.1 / CUDA 12.8 / cuDNN 9.10.0.2)
|
|
0
|
85
|
June 2, 2026
|
|
How does autograd deal with minibatches?
|
|
1
|
93
|
May 29, 2026
|
|
Using Jax code with PyTorch code
|
|
16
|
2518
|
May 26, 2026
|
|
Plotting the gradient computation graph including values
|
|
0
|
60
|
April 15, 2026
|
|
Segmentation fault when calling .backward() after moving data to GPU (PyTorch + CUDA 12.1)
|
|
8
|
482
|
April 14, 2026
|
|
How to get the version numbers of a Module's Parameters?
|
|
5
|
1001
|
March 13, 2026
|
|
Requires_grad becomes false after some operation
|
|
3
|
157
|
March 3, 2026
|
|
Problem of freeze metrics after first epoch
|
|
1
|
99
|
February 28, 2026
|
|
Function 'Scaled Dot Product Efficient Attention Backward0' returned nan values in its 0th output
|
|
13
|
2358
|
February 9, 2026
|
|
RNN memory management: RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation
|
|
2
|
120
|
February 6, 2026
|
|
About the sign of gradients from token probability w.r.t. intermediate activations during inference
|
|
1
|
96
|
January 12, 2026
|
|
Using `forward_pre_hook` to attribute CUDA OOMs to module execution context
|
|
2
|
129
|
January 8, 2026
|
|
PyTorch CPU RAM Usage Grows Rapidly When Assembling Forces from CNN Output—How to Prevent Memory Leak?
|
|
0
|
92
|
December 11, 2025
|
|
Simple extension of autograd saved tensor hook mechanism
|
|
4
|
182
|
December 10, 2025
|
|
Does scaled_dot_product_attention's backward support reproduce
|
|
0
|
83
|
December 10, 2025
|
|
How to make a manually changed loss work in backpropagation
|
|
1
|
97
|
December 3, 2025
|
|
torch.autograd.Function and free function
|
|
2
|
120
|
December 3, 2025
|
|
Autograd and dead-code elimination
|
|
2
|
176
|
November 18, 2025
|
|
Does PyTorch muon optimizer supports 4D weights?
|
|
1
|
199
|
November 17, 2025
|
|
Gradient ascent on some parameters while descent on others in a single model
|
|
3
|
165
|
November 11, 2025
|
|
Batchnorm and back-propagation
|
|
8
|
4232
|
November 3, 2025
|
|
How to debug origin of nans in gradient of custom module
|
|
3
|
177
|
October 29, 2025
|
|
Optimizing a mask instead of weights
|
|
2
|
177
|
October 27, 2025
|
|
PyTorch AD with non-python functions
|
|
1
|
99
|
October 22, 2025
|