Search results

# [QNN] AttributeError: 'list' object has no attribute 'key' when using fp_node_id_set

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/

Status: Open.

Bug

#18996 In pytorch/executorch;

· KevinUW114514 opened on Apr 20, 2026

[QNN] KeyError: 'aten.pow.Scalar' — LiftConstantScalarOperands misses aten.pow.Scalar in SCALAR_OPS (and crashes on float arg)

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/

Status: Open.

Bug

#18993 In pytorch/executorch;

· KevinUW114514 opened on Apr 20, 2026

[RFC] First-class RISC-V support in ExecuTorch

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.

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.

Feature

#18991 In pytorch/executorch;

· luhenry opened on Apr 19, 2026

[QNN] AttributeError in _mark_nodes_as_annotated when a layer_norm node has optional weight as None

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/

Status: Open.

Bug

#18989 In pytorch/executorch;

· KevinUW114514 opened on Apr 19, 2026

Arm backend: Quantized aten.cat constant-fold bug with list-valued tensor inputs

partner: armFor backend delegation, kernels, demo, etc. from the 3rd-party partner, ArmFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm

Status: Open.

#18971 In pytorch/executorch;

· Rob-Hughes-Arm opened on Apr 17, 2026

[qnn] about the new arch chipset and larger models

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/

Status: Open.

#18964 In pytorch/executorch;

· ecccccsgo opened on Apr 17, 2026

Android ET APIs : Path to Stable (From Experimental)

module: androidIssues related to Android code, build, and executionIssues related to Android code, build, and execution

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.

#18950 In pytorch/executorch;

· psiddh opened on Apr 16, 2026

[AOTI-CUDA] qwen3.5-35B-A3B prefill int8 perf through MoE

Status: Open.

Feature

#18949 In pytorch/executorch;

· digantdesai opened on Apr 16, 2026

XNNPACK weights cache crashes on null pointer

module: androidIssues related to Android code, build, and executionIssues related to Android code, build, and execution

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

#18946 In pytorch/executorch;

· jgibson2 opened on Apr 16, 2026

Deprecate to_edge_transform_and_lower_to_qnn and to_edge_transform_and_lower_to_enn

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.

#18945 In pytorch/executorch;

· abhinaykukkadapu opened on Apr 16, 2026

ChannelsLastTaggedReshapePass crashes with immutable_list when using dynamic 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

#18944 In pytorch/executorch;

· jgibson2 opened on Apr 16, 2026

[QNN] Performace degradation Qwen0.6 on Qnn Backend.

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/

Status: Open.

#18933 In pytorch/executorch;

· yinrun opened on Apr 16, 2026