Search results

On the same device (8295), Qwen3-0.6B and Qwen3-1.7B exhibit different CPU utilization, with Qwen3-0.6B showing higher CPU usage.

Status: Open.

#15998 In pytorch/executorch;

· lansexinhu opened on Nov 27, 2025

Something wrong in executorch/extension/training /README.md

Status: Open.

#15991 In pytorch/executorch;

· qqqqqqqwy opened on Nov 26, 2025

[QNN] QualComm latest SM8850 doesn't support

module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/

partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm

Status: Open.

#15986 In pytorch/executorch;

· yinrun opened on Nov 26, 2025

[QNN] Multi-graph models fail on second iteration with DMA execution error 1100

module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/

partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm

Status: Open.

#15985 In pytorch/executorch;

· notaJiminLee opened on Nov 26, 2025

qnn_executor_runner - mismatch in the skel files ?

module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/

partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm

Status: Open.

Bug

#15978 In pytorch/executorch;

· eliyam32 opened on Nov 25, 2025

What should I do if there is SoC for my processor?

module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/

partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm

Status: Open.

Feature

#15973 In pytorch/executorch;

· kejndan opened on Nov 25, 2025

Update doc links for 1.0.1

Status: Open.

#15966 In pytorch/executorch;

· GregoryComer opened on Nov 24, 2025

Add warning when users use to_edge instead of to_edge_transform_and_lower with CoreML

good first issueGood for newcomersGood for newcomers

Status: Open.

#15960 In pytorch/executorch;

· metascroy opened on Nov 24, 2025

qnn_llama_runner on SA8295 outputs repetitive “sp” with Qwen3-1.7B after ExecuTorch export

module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/

partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm

Status: Open.

Feature

#15954 In pytorch/executorch;

· lansexinhu opened on Nov 24, 2025

CUDA backend benchmark ci

Status: Open.

#15921 In pytorch/executorch;

· Gasoonjia opened on Nov 20, 2025

Add segments for bpte

Status: Open.

#15874 In pytorch/executorch;

· lucylq opened on Nov 18, 2025

Pybindings for flat tensor

Status: Open.

#15873 In pytorch/executorch;

· lucylq opened on Nov 18, 2025