Skip to content

Issues: pytorch/executorch

[v0.5.0] Release Tracker
#7344 opened Dec 17, 2024 by SS-JIA
Open 2
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.

Sign up for GitHub

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

262 Open 316 Closed
262 Open 316 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Llama3.2 unable to perform batch inference on Android
#7435 opened Dec 24, 2024 by chienhuikuo
cannot import name 'default_decompositions' from 'torch.export' (Pytorch & Executorch issues)
#7434 opened Dec 24, 2024 by ApexIllumination
Perhaps a bug with op aten.split_with_sizes? module: mps Issues related to Apple's MPS delegation partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#7430 opened Dec 23, 2024 by Metakar1
1
Failed to export ViT model to QNN with quant_dtype set to None module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#7429 opened Dec 23, 2024 by Metakar1
2
I am trying to use export custom model to a executorch module: exir Issues related to Export IR
#7428 opened Dec 23, 2024 by dinusha94
1
buck2 needs to be updated past https://github.com/facebook/buck2/pull/693 (June 28, 2024) so executorch can build on Raspberry Pi 5
#7425 opened Dec 22, 2024 by swolchok
1
Llama 3.2 1B model bad response.
#7424 opened Dec 22, 2024 by Jayantparashar10
ARM ML embedded evaluation Kit support 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
#7423 opened Dec 22, 2024 by dinusha94
@digantdesai
4
Cannot install executorch on M series macbook - install_requirements.sh fails
#7419 opened Dec 20, 2024 by byjlw
4
comparison with qualcomm ai hub model
#7411 opened Dec 20, 2024 by DongGeun123
Remove patch for QNN to use the legacy export flow.
#7373 opened Dec 18, 2024 by lucylq
tinyllama w/ mps error when running on ios benchmark app bug Something isn't working module: benchmark Features or issues related to benchmark infra, including the workflow, CI and benchmark apps triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#7366 opened Dec 18, 2024 by guangy10
@shoumikhin
1
Support qcs6490 v68 arch for QNN backend 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
#7356 opened Dec 18, 2024 by amo33
1
insert_write_back_for_buffers_pass should inject copy_ nodes at the earliest possible spot. bug Something isn't working module: exir Issues related to Export IR
#7345 opened Dec 17, 2024 by JacobSzwejbka
[v0.5.0] Release Tracker
#7344 opened Dec 17, 2024 by SS-JIA
2
Executorch Vulkan delegate fails to build vulkan_executor_runner without NDK module: vulkan triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#7343 opened Dec 17, 2024 by alexggener
@SS-JIA
7
Publish Linux ARM64 Wheels to PyPI actionable Items in the backlog waiting for an appropriate impl/fix feature A request for a proper, new feature. triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#7331 opened Dec 16, 2024 by johnthagen
2
Missing libflatccrt.a when building executor_runner 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
#7300 opened Dec 12, 2024 by benkli01
2
executorch 0.4.0: module 'executorch' has no attribute '__version__'
#7292 opened Dec 11, 2024 by guangy10
1
export llama 3.2-1B error with executorch 4.0 and main branch module: llm LLM examples and apps, and the extensions/llm libraries triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#7263 opened Dec 10, 2024 by fighting300
1
The extension headers are missing after installation Android Android building and execution related. module: doc Related to our documentation, both in docs/ and docblocks triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#7261 opened Dec 10, 2024 by fiberflow
3
Flatc should be built for the host rather than the target when cross-compiling
#7260 opened Dec 10, 2024 by fiberflow
In llama demo readme, remind people that they can also download from HF
#7244 opened Dec 9, 2024 by mergennachin
A warning/note message for reminding people to clone submodule after the first clone.
#7243 opened Dec 9, 2024 by mergennachin
A simple build_demo.sh script for Llama
#7242 opened Dec 9, 2024 by mergennachin
ProTip! Updated in the last three days: updated:>2024-12-21.