Search results

Update coremltools to use torchao.quantization.pt2e.quantizer instead of deprecated torch.ao.quantization.quantizer

Status: Open.

Bug

#16484 In pytorch/executorch;

· psiddh opened on Jan 7, 2026

Update ET XNNPACK dependency

Status: Open.

#16472 In pytorch/executorch;

· GregoryComer opened on Jan 6, 2026

Analyze CPU operator performance

Status: Open.

#16471 In pytorch/executorch;

· GregoryComer opened on Jan 6, 2026

Implement BoxWithNMSLimit custom op

Status: Open.

#16470 In pytorch/executorch;

· GregoryComer opened on Jan 6, 2026

QNN HTP init fails on CQ8750S (soc_id=705): "No Snapdragon SOC detected"

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.

#16465 In pytorch/executorch;

· INHA-SW opened on Jan 6, 2026

Lowered parameter with channels last dim order is actually stored as contiguous

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

Status: Open.

Bug

#16464 In pytorch/executorch;

· MartinPavella opened on Jan 6, 2026

Error during quantizing the executorch model

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.

#16432 In pytorch/executorch;

· VEERA-NAGENDRA-KUMAR-EETHA opened on Jan 5, 2026

Dequantize_per_channel produces incorrect output with channels last dim order

Status: Open.

Bug

#16429 In pytorch/executorch;

· MartinPavella opened on Jan 5, 2026

Exception: An error occurred when running the 'InsertIOQDQ' pass after the following passes: ['FoldQDQ', 'InsertRequantize']

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.

#16427 In pytorch/executorch;

· ThreeD-H opened on Jan 4, 2026

Accuracy drop : DeiT-tiny & LLaMA behavior differences between FP / Decomposition / FQ / TOSA

module: armIssues related to arm backendIssues related to arm backend

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.

#16426 In pytorch/executorch;

· hth000 opened on Jan 2, 2026

java linux cannot work , we need executorch java jar format package ，please support

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

Status: Open.

#16422 In pytorch/executorch;

· mullerhai opened on Dec 31, 2025

Batch Inference On 8255 device

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.

#16413 In pytorch/executorch;

· imjking opened on Dec 30, 2025