empty tensor moving to default device #2948
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
component: lowering
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
There are some changes that do not conform to Python style guidelines:
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/_decompositions.py 2024-06-24 21:23:46.440916+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/lowering/_decompositions.py 2024-06-24 21:25:39.065443+00:00
@@ -170,11 +170,11 @@
empty_size = args[0]
empty_permute = args[1]
perm = [0] * len(empty_size)
for permute_index, permute_element in enumerate(empty_permute):
perm[permute_element] = permute_index
- default_device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+ default_device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
kwargs[device] = default_device
return torch.empty([empty_size[l] for l in empty_permute], **kwargs).permute(perm)
@register_torch_trt_decomposition(
@@ -233,12 +233,14 @@
torch.ops.aten.empty_strided.default, registry=TORCH_TRT_DECOMPOSITIONS
)
def empty_strided_decomposition(*args, **kwargs) -> torch.Tensor:
empty_size = args[0]
empty_stride = args[1]
- default_device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
- return torch.as_strided(torch.empty(empty_size, device = default_device), empty_size, empty_stride)
+ default_device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+ return torch.as_strided(
+ torch.empty(empty_size, device=default_device), empty_size, empty_stride
+ )
def get_decompositions(
enable_experimental_decompositions: bool = False,
) -> Dict[OpOverload, Callable[[Any], Any]]:
apbose
force-pushed
the
torchTRT_empty_decomp_device_fix
branch
from
5431f29 to
7f8bb4f
Compare
apbose
force-pushed
the
torchTRT_empty_decomp_device_fix
branch
from
7f8bb4f to
c67cad5
Compare
peri044
requested changes
Jun 24, 2024
| @@ -172,6 +172,8 @@ def empty_permuted_decomposition(*args, **kwargs) -> torch.Tensor: | |||
| perm = [0] * len(empty_size) | |||
| for permute_index, permute_element in enumerate(empty_permute): | |||
| perm[permute_element] = permute_index | |||
| default_device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |||
There was a problem hiding this comment.
use the default device defined in our _defaults.py : https://github.com/pytorch/TensorRT/blob/main/py/torch_tensorrt/dynamo/_defaults.py#L37
and convert this into a torch device via _enums.to()
| @@ -233,7 +235,10 @@ def select_scatter_decomposition( | |||
| def empty_strided_decomposition(*args, **kwargs) -> torch.Tensor: | |||
| empty_size = args[0] | |||
| empty_stride = args[1] | |||
| return torch.as_strided(torch.empty(empty_size), empty_size, empty_stride) | |||
| default_device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |||
cehongwang
pushed a commit
that referenced
this pull request
Jul 8, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.