github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-05 19:13:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

[misc] update pre-commit and run all files (#4752)

Browse Source 
* [misc] update pre-commit

* [misc] run pre-commit

* [misc] remove useless configuration files

* [misc] ignore cuda for clang-format
This commit is contained in:
Hongxin Liu
2023-09-19 14:20:26 +08:00
committed by GitHub
parent 3c6b831c26
commit 079bf3cb26
1268 changed files with 50037 additions and 38444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
colossalai/legacy/nn/loss/loss_1d.py
View File

@@ -9,7 +9,6 @@ from colossalai.legacy.registry import LOSSES
class _VocabParallelCrossEntropy1D(torch.autograd.Function):
@staticmethod
@custom_fwd(cast_inputs=torch.float32)
def forward(ctx, vocab_parallel_logits, targets, process_group):
@@ -61,7 +60,6 @@ class _VocabParallelCrossEntropy1D(torch.autograd.Function):
@staticmethod
@custom_bwd
def backward(ctx, grad_output):
# Retrieve tensors from the forward path.
softmax, target_mask, masked_target_1d = ctx.saved_tensors
@@ -73,7 +71,7 @@ class _VocabParallelCrossEntropy1D(torch.autograd.Function):
# Add the gradient from matching classes.
arange_1d = torch.arange(start=0, end=grad_2d.size()[0], device=grad_2d.device)
grad_2d[arange_1d, masked_target_1d] -= (1.0 - target_mask.view(-1).float())
grad_2d[arange_1d, masked_target_1d] -= 1.0 - target_mask.view(-1).float()
# Finally elementwise multiplication with the output gradients.
grad_input.mul_(grad_output.unsqueeze(dim=-1))