issues Search Results · repo:pytorch/executorch language:Python
Filter by
610 results
(64 ms)610 results
inpytorch/executorch (press backspace or delete to remove)🐛 Describe the bug
Models with replication_pad3d decomposed and partially delegated to vulkan error out with a missing shader error (see
below).
import torch
from executorch.backends.vulkan.partitioner.vulkan_partitioner ...
backend tester
module: vulkan
GregoryComer
- Opened 1 minute ago
- #12226
🐛 Describe the bug
Vulkan models containing torch.linalg.norm can fail to partition with an index out of range error.
import torch
from executorch.backends.vulkan.partitioner.vulkan_partitioner import ...
backend tester
module: vulkan
- Opened 8 minutes ago
- #12225
🐛 Describe the bug
Some models containing avgpool1d ops delegated to Vulkan fail to load with following error: IndexError:
vector::_M_range_check: __n (which is 18446744073709551614) = this- size() (which ...
backend tester
module: vulkan
- Opened 19 minutes ago
- #12224
🐛 Describe the bug
When running transposed 1d convolutions with non-zero padding, outputs appear to differ on Vulkan from
eager/portable. 2d convs match eager, so it appears to be specific to 1d.
import ...
backend tester
module: vulkan
- Opened 44 minutes ago
- #12223
🐛 Describe the bug
When running the following repro on the Vulkan delegate, outputs differ from eager mode. ET portable matches eager.
import torch
from executorch.backends.vulkan.partitioner.vulkan_partitioner ...
backend tester
module: vulkan
- Opened 1 hour ago
- #12222
🚀 The feature, motivation and pitch
https://github.com/pytorch/executorch/blob/main/tools/cmake/Utils.cmake#L89 here, there is no ANDROID_ABI=armeabi-v7a
option, so if i want to build executorch for ANDROID_ABI=armeabi-v7a, ...
barbecacov
- Opened 3 hours ago
- #12221
mergennachin
- Opened 8 hours ago
- #12216
- Opened 8 hours ago
- #12215
Current status quo:
ET Website: https://docs.pytorch.org/executorch/stable/llm/llama.html
https://docs.pytorch.org/executorch/stable/llm/llama-demo-android.html
https://docs.pytorch.org/executorch/stable/llm/llama-demo-ios.html ...
- Opened 8 hours ago
- #12214
I m disabling the workflow to investigate why it s cancelled. We currently don t get any useful signals out of it anyway
because of the cancellation
https://github.com/pytorch/executorch/actions/workflows/apple-perf-private-device-experiment.yml. ...
huydhn
- Opened 11 hours ago
- #12211
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!
Restrict your search to the title by using the in:title qualifier.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!
Restrict your search to the title by using the in:title qualifier.