List view

All GA models export to CoreML via. torch.export with the same performance and user experience as torch.jit.trace

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

Task

#9610 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

All GA models are supported by CoreML and have similar performance to using CoreML via torch.export

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

Task

#9614 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

Enumerated shape support

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9622 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

Continuous coverage and performance monitoring of GA models for CoreML backend.

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9625 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

Establish a process for monitoring and resolving CoreML GH issues, including an SLA

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9626 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

CI to cover different iOS versions

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9628 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

Support better tiling algorithms for ANE

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9630 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

Improve CoreML model loading time

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9631 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

Improve GPU performance

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9629 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

CoreML quantization is supported by PyTorch flows (PT2E).

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#9617 In pytorch/executorch;

· metascroy opened on Mar 25, 2025

Enable MobileBert and Albert with XNNPACK quantization

module: xnnpackIssues related to xnnpack delegation and the code under backends/xnnpack/Issues related to xnnpack delegation and the code under backends/xnnpack/

Status: Open.

Bug

#12341 In pytorch/executorch;

· mergennachin opened on Jul 10, 2025

Make swin2sr_2x and trocr_handwritten models to be exportable

Status: Open.

#12365 In pytorch/executorch;

· mergennachin opened on Jul 10, 2025

Add more representative models for diverse as part of GA++ models

Status: Open.

Task

#12378 In pytorch/executorch;

· mergennachin opened on Jul 10, 2025

[Sprint 3] QB4 Packing Kernels in KleidiAI

Status: Open.

#11932 In pytorch/executorch;

· mcr229 opened on Jun 24, 2025

[Sprint 2][Performance Fine Tuning] Hugging Face Transformer Models

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

Task

#12467 In pytorch/executorch;

· mcr229 opened on Jul 14, 2025

[Sprint 4] Make Workspace Sharing Default

Status: Open.

#12502 In pytorch/executorch;

· mcr229 opened on Jul 15, 2025

[Sprint 4] Make Weight Sharing Default

module: runtimeIssues related to the core runtime and code under runtime/Issues related to the core runtime and code under runtime/

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

Feature

#12503 In pytorch/executorch;

· mcr229 opened on Jul 15, 2025

[Sprint 1][Performance Fine Tuning] ExecuTorch Example Models

module: examplesIssues related to demos under examples/Issues related to demos under examples/

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

Task

#12466 In pytorch/executorch;

· mcr229 opened on Jul 14, 2025

Verify e2e perf uplift after inplacing Portable index_put

module: kernelsIssues related to kernel libraries and utilities, and code under kernels/Issues related to kernel libraries and utilities, and code under kernels/

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

Task

#12565 In pytorch/executorch;

· digantdesai opened on Jul 16, 2025

[Delegate Testing] Add Support for Arm Ethos-U backend (AOT)

actionableItems in the backlog waiting for an appropriate impl/fixItems in the backlog waiting for an appropriate impl/fix

module: armIssues related to arm backendIssues related to arm backend

Status: Open.

Feature

#12811 In pytorch/executorch;

· digantdesai opened on Jul 24, 2025

[Arm] Size-test: Run the binary on CI

actionableItems in the backlog waiting for an appropriate impl/fixItems in the backlog waiting for an appropriate impl/fix

good first issueGood for newcomersGood for newcomers

module: armIssues related to arm backendIssues related to arm backend

Status: Open.

Task

#12812 In pytorch/executorch;

· digantdesai opened on Jul 24, 2025

[Embedded] Finalize and Enable GA models on Cortex-M FVP

module: armIssues related to arm backendIssues related to arm backend

module: microcontrollersFor embedded MCUs like Cortex-M, or RTOS like Zephyr, does not track NPU backend like Arm Ethos.For embedded MCUs like Cortex-M, or RTOS like Zephyr, does not track NPU backend like Arm Ethos.

Status: Open.

Task

#12901 In pytorch/executorch;

· digantdesai opened on Jul 28, 2025

[Embedded] [Cortex-M] Improve performance of quantized MV2 or 3 performance using Arm CMSIS-NN

module: armIssues related to arm backendIssues related to arm backend

module: microcontrollersFor embedded MCUs like Cortex-M, or RTOS like Zephyr, does not track NPU backend like Arm Ethos.For embedded MCUs like Cortex-M, or RTOS like Zephyr, does not track NPU backend like Arm Ethos.

Status: Open.

Task

#12902 In pytorch/executorch;

· digantdesai opened on Jul 28, 2025

[Embedded] Top level task to track SDK integrations

module: microcontrollersFor embedded MCUs like Cortex-M, or RTOS like Zephyr, does not track NPU backend like Arm Ethos.For embedded MCUs like Cortex-M, or RTOS like Zephyr, does not track NPU backend like Arm Ethos.

Status: Open.

Task

#12903 In pytorch/executorch;

· digantdesai opened on Jul 28, 2025

[Portable] Enable CI for new GA+ models

module: kernelsIssues related to kernel libraries and utilities, and code under kernels/Issues related to kernel libraries and utilities, and code under kernels/

Status: Open.

Task

#12911 In pytorch/executorch;

· digantdesai opened on Jul 28, 2025