issues Search Results · repo:pytorch/executorch language:Python
Filter by
0 results
(67 ms)0 results
inpytorch/executorch (press backspace or delete to remove)🐛 Describe the bug
The following model errors out during lowering on Core ML:
import torch
from executorch.backends.apple.coreml.partition import CoreMLPartitioner
from executorch.exir import to_edge_transform_and_lower, ...
backend tester
module: coreml
GregoryComer
- Opened 6 hours ago
- #11706
🐛 Describe the bug
The following repro fails to lower on Core ML. It uses ConvTranspose2d, but 1d and 3d appear to fail similarly.
import torch
from executorch.backends.apple.coreml.partition import ...
backend tester
module: coreml
- Opened 6 hours ago
- #11705
🐛 Describe the bug
The following repro produces an artifact that can t run at runtime. I haven t looked deeply yet to figure out where the
issue is, so this needs more triage. Might be in the pytorch ...
backend tester
module: exir
module: kernels
- Opened 6 hours ago
- #11704
🐛 Describe the bug
Models with a convolution using padding_mode= circular on Core ML error out during lowering.
Repro:
import torch
from executorch.backends.apple.coreml.partition import CoreMLPartitioner ...
backend tester
module: coreml
- Opened 7 hours ago
- #11703
🐛 Describe the bug
Models with InstanceNorm3d on the Core ML backend fail to load at runtime.
Repro:
import torch
from executorch.backends.apple.coreml.partition import CoreMLPartitioner
from executorch.exir ...
backend tester
module: coreml
- Opened 7 hours ago
- #11702
🐛 Describe the bug
When running BatchNorm3d ops on Core ML, it appears to crash the process pretty regularly.
Repro:
import torch
from executorch.backends.apple.coreml.partition import CoreMLPartitioner ...
backend tester
module: coreml
- Opened 7 hours ago
- #11701
🐛 Describe the bug
When using an in-place activations (tested on relu and elu), it appears to alter the graph outputs. I m not entirely
sure what the expected behavior is, but this seems incorrect.
In ...
backend tester
module: exir
- Opened 8 hours ago
- #11700
🐛 Describe the bug
CoreML partitioner is missing a constraint for sorted=False on iOS 16. It errors out during lowering, but should not
partition to allow it to fall back to portable or another backend. ...
backend tester
module: coreml
- Opened yesterday
- #11698
🐛 Describe the bug
CoreML only supports dilation=1 for max pool. However, it s missing a partitioner constraint, so models with a pooling
op with dilation 1 will error out. It should just be not partitioned ...
backend tester
module: coreml
- Opened yesterday
- #11697
🐛 Describe the bug
The following model fails to lower:
import torch
from executorch.backends.apple.coreml.partition import CoreMLPartitioner
from executorch.exir import to_edge_transform_and_lower
from ...
backend tester
module: coreml
- Opened yesterday
- #11696
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.