-
Notifications
You must be signed in to change notification settings - Fork 299
Issues: pytorch/executorch
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[CoreML] Upsample Bilinear antialias = True is not supported
enhancement
Not as big of a feature, but technically not a bug. Should be easy to fix
module: coreml
Issues related to Apple's Core ML delegation
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5728
opened Sep 27, 2024 by
cccclai
Core ML Backend CoreMLBackend is not registered.
bug
Something isn't working
module: coreml
Issues related to Apple's Core ML delegation
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5722
opened Sep 27, 2024 by
ismaeelbashir03
Slow model loading time for CoreML quantized model
module: coreml
Issues related to Apple's Core ML delegation
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5718
opened Sep 27, 2024 by
cccclai
Support for LLaVA-NeXT
feature
A request for a proper, new feature.
module: runtime
Issues related to core runtime
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5712
opened Sep 26, 2024 by
pal9000i
Python run_method API segfaults if given non-existent method
enhancement
Not as big of a feature, but technically not a bug. Should be easy to fix
module: extension
Related to extension built on top of runtime, e.g. pybindings, data loader, etc.
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5648
opened Sep 25, 2024 by
swolchok
Partial weight loading for reduced RAM utilization
feature
A request for a proper, new feature.
module: runtime
Issues related to core runtime
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5626
opened Sep 25, 2024 by
kushalpatil07
Building Llama IOS Demo failed
bug
Something isn't working
module: examples
Issues related to demos under examples directory
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5623
opened Sep 25, 2024 by
Hanxian97
v0.4.0-rc2 Android Demo App for Llama crashing on Pixel 8 when first prompt submitted
Android
Android building and execution related.
bug
Something isn't working
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5582
opened Sep 24, 2024 by
grisaitis
macOS: standard include files not found; requires installing/activating Xcode
bug
Something isn't working
module: build
Related to buck2 and cmake build
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5570
opened Sep 23, 2024 by
guangy10
Core ML perf regression observed on non-genai models
module: coreml
Issues related to Apple's Core ML delegation
partner: apple
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Apple
#5564
opened Sep 23, 2024 by
guangy10
Running aten::add.out instead of aten::_softmax.out leads to FLASH overflow
bug
Something isn't working
partner: arm
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5544
opened Sep 23, 2024 by
ChristophKarlHeck
phi-3-mini is not a valid Python package name
bug
Something isn't working
module: examples
Issues related to demos under examples directory
#5509
opened Sep 20, 2024 by
sbrugman
Is it possible to use Qualcomm Backend & ExecuTorch (experimental) training?
module: qnn
Related to Qualcomm's QNN delegate
module: training
partner: qualcomm
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#5417
opened Sep 17, 2024 by
escorciav
Operator torch._ops.aten.unfold.default is not Aten Canonical
module: exir
Issues related to Export IR
#5381
opened Sep 15, 2024 by
ari-ruokamo
xnnpack backend fails on convolutions after export.save -> export.load
bug
Something isn't working
module: exir
Issues related to Export IR
module: xnnpack
Issues related to xnnpack delegation
#5265
opened Sep 11, 2024 by
mads-oestergaard
Android native crash when running Executorch Demo with ic4_xnnpack_fp32.pte
Android
Android building and execution related.
#5264
opened Sep 11, 2024 by
YuHayring
"There appear to be 1 leaked semaphore objects to clean up at shutdown" while llava export
#5171
opened Sep 9, 2024 by
JLake310
The calculation results of RoPE implemented by executorch and C++ are different.
#5170
opened Sep 9, 2024 by
connieKing511
dl3 model fails to export with coreml delegates
bug
Something isn't working
module: coreml
Issues related to Apple's Core ML delegation
module: examples
Issues related to demos under examples directory
partner: apple
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Apple
#5159
opened Sep 6, 2024 by
guangy10
vit model fails to export with coreml delegates
bug
Something isn't working
module: coreml
Issues related to Apple's Core ML delegation
module: examples
Issues related to demos under examples directory
partner: apple
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Apple
#5157
opened Sep 6, 2024 by
guangy10
Is there any way or tool to visualize
module: devtools
Features or issues related to profiling, debugging, bundled program, etc.
#5110
opened Sep 5, 2024 by
ContCh
RuntimeError: mmap can only be used with files saved with torch.save and _use_new_zipfile_serialization=True
llm: evaluation
Perplexity, accuracy
#5030
opened Sep 3, 2024 by
MisssssXie
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.