Skip to content

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.

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

200 Open 284 Closed
200 Open 284 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

Cannot export quantized resnet50_clip.openai model to Edge dialect
#6685 opened Nov 6, 2024 by corehalt
1
[QNN ISSUE] QNN 16a8w Quantization Method for the Llama-3.2 Model.
#6684 opened Nov 6, 2024 by crinex
2
Model lowers to CoreML but fails to run module: coreml Issues related to Apple's Core ML delegation
#6663 opened Nov 5, 2024 by margaritaG
How To Building and Running Llama 3.2 1B Instruct with Qualcomm AI Engine Direct Backend？
#6655 opened Nov 5, 2024 by baotonghe
5
Support Numpy 2.0
#6639 opened Nov 4, 2024 by YifanShenSZ
aten::_native_batch_norm_legit.no_stats_out Check failed (training == false): Portable kernels only support inference mode!
#6632 opened Nov 4, 2024 by githubpeichao
3
Question Regarding Code Execution in the Calibration Process.
#6629 opened Nov 3, 2024 by crinex
@cccclai
2
error: 'realpath' was not declared in this scope when building ExecuTorch on ARM partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm
#6593 opened Oct 31, 2024 by AIWintermuteAI
2
Inquired for Llama-3.2-1&3B-INT4-E08 SpinQuant Rotation Matrix Generation Command. module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#6584 opened Oct 31, 2024 by crinex
1
Android: Tensor type is not very friendly to BFloat16 Android Android building and execution related.
#6571 opened Oct 29, 2024 by JamePeng
1
RFC: Java layer EValue serialization
#6569 opened Oct 29, 2024 by kirklandsign
@JacobSzwejbka
6
RFC: extension/llm API design
#6558 opened Oct 29, 2024 by larryliu0820
[QNN ISSUE] Error Occurred When Running Llama-3.2-1B-Instruct Model with llama_main (QNN 8A8W Quantization) on Device module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#6546 opened Oct 29, 2024 by crinex
4
mobilenetv2 doesn't work with Vulkan backend module: vulkan
#6516 opened Oct 28, 2024 by sternezsl
@SS-JIA
2
TTFT takes too long module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#6514 opened Oct 28, 2024 by justin-Kor
3
LLaVA example fails with error module: build Related to buck2 and cmake build
#6512 opened Oct 27, 2024 by hannakoepcke
1
qd8-f16 quantization in xnnpack module: xnnpack Issues related to xnnpack delegation
#6510 opened Oct 26, 2024 by mads-oestergaard
1
Schema for data-only file rfc Request for comment and feedback on a post, proposal, etc. triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#6492 opened Oct 24, 2024 by lucylq
@lucylq
C++ includes require that the repo lives in a directory named exactly executorch
#6475 opened Oct 24, 2024 by dbort
1
AOSP related issues 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
#6470 opened Oct 23, 2024 by kirklandsign
@davidlin54 @kirklandsign
14
Is there a way to manipulate the model's key/value cache or tokenizer's outputs in Android?
#6464 opened Oct 23, 2024 by 1010asdf0101
@larryliu0820 @kirklandsign
1
Build Android aar failed due to lacking crypt.h module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#6454 opened Oct 23, 2024 by hsyodyssey
@cccclai @kirklandsign
4
Llama 3 QNN export docs hard to find module: doc Related to our documentation, both in docs/ and docblocks 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
#6436 opened Oct 22, 2024 by Riandy
@mergennachin @cccclai
2
build error when generate llama2 exe file in x86 computer
#6431 opened Oct 22, 2024 by l2002924700
@larryliu0820 @tarun292
2
Error from LLaMA 3.2 3B Instruct Model generation (.pte) module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#6388 opened Oct 21, 2024 by justin-Kor
@cccclai
16
ProTip! Find all open issues with in progress development work with linked:pr.