github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-25 19:55:03 +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

14
colossalai/auto_parallel/meta_profiler/meta_registry/pooling.py
View File

@@ -63,7 +63,7 @@ def avgpool_meta_info(*args, **kwargs) -> Tuple[TrainCycleItem, TrainCycleItem,
# store fwd_in, fwd_buffer, fwd_out
fwd_in = []
fwd_buffer = []
fwd_out = [torch.zeros_like(output_tensor, device='meta')]
fwd_out = [torch.zeros_like(output_tensor, device="meta")]
return compute_cost, mem_cost, fwd_in, fwd_buffer, fwd_out
@@ -117,8 +117,10 @@ def maxpool_meta_info(*args, **kwargs) -> Tuple[TrainCycleItem, TrainCycleItem,
fwd_mem_cost = MemoryCost(activation=compute_size_in_bytes([input_tensor, output_tensor, index_matrix]))
# temp memory for backward is the index matrix to be discarded
bwd_mem_cost = MemoryCost(activation=compute_size_in_bytes(input_tensor) - compute_size_in_bytes(index_matrix),
temp=compute_size_in_bytes(index_matrix))
bwd_mem_cost = MemoryCost(
activation=compute_size_in_bytes(input_tensor) - compute_size_in_bytes(index_matrix),
temp=compute_size_in_bytes(index_matrix),
)
# total cost
total_mem_cost = MemoryCost(activation=fwd_mem_cost.activation + bwd_mem_cost.activation, temp=bwd_mem_cost.temp)
@@ -126,8 +128,8 @@ def maxpool_meta_info(*args, **kwargs) -> Tuple[TrainCycleItem, TrainCycleItem,
mem_cost = TrainCycleItem(fwd=fwd_mem_cost, bwd=bwd_mem_cost, total=total_mem_cost)
# store fwd_in, fwd_buffer, fwd_out
fwd_in = [torch.zeros_like(input_tensor, device='meta')]
fwd_buffer = [torch.zeros_like(index_matrix, device='meta')]
fwd_out = [torch.zeros_like(output_tensor, device='meta')]
fwd_in = [torch.zeros_like(input_tensor, device="meta")]
fwd_buffer = [torch.zeros_like(index_matrix, device="meta")]
fwd_out = [torch.zeros_like(output_tensor, device="meta")]
return compute_cost, mem_cost, fwd_in, fwd_buffer, fwd_out