executorch

executorch copied to clipboard

Qualcomm AI Engine Direct - GLM1.5B

2

### Summary GLM Enablement `python examples/qualcomm/oss_scripts/llama/llama.py -b build-android -s $DEVICE -m SM8750 --temperature 0 --model_mode kv --max_seq_len 128 --decoder_model glm-1_5b --prompt "Could you tell me about Facebook?"` ### Test plan...

winskuo-quic

Frozen weight on cuda delegate

2

frozen weight on cuda delegate for better perf

Gasoonjia

Pytest has released version 9.0, but we are seeing test failures after upgrading ([example job](https://github.com/pytorch/executorch/actions/runs/19308882645/job/55223581796)). I'm pinning pytest

GregoryComer

Error in minimal example code for export with vulken as backend

2

### 🐛 Describe the bug python code： ```python import torch from torch.export import export from executorch.exir import to_edge from executorch.backends.vulkan.partitioner.vulkan_partitioner import VulkanPartitioner # Start with a PyTorch model that adds...

songhat

QNN export failure for PARSeq text recognition model

1

### 🐛 Describe the bug I have a fork of the PARSeq repository with slight modifications for Executorch compatibility that is failing to export for QNN using the build_executorch_binary method....

Fredrik00

Added more users to exclude

2

Chenweng-quic MatthiasHertel80 (Arm) Michaelmaitland (Meta internal) RahulC7 (Meta internal) can update author jorgep31415 to Juniper Pineda: https://github.com/junpi3 Young Han - Meta - https://github.com/seyeong-han Mitch Bailey - https://github.com/jmahbs (Arm) Alex Tawse...

nil-is-all

Add qwen 2.5 for llama app

6

Summary: Generate qwen2.5 0.5b model and run on the app Differential Revision: D81751900

cccclai

Replace fixed number cmake --build -j in sh and docs #10887

6

## Summary Replaces fixed number of cmake --build -j entries with: mac: -j$(($(sysctl -n hw.ncpu) - 1)) linux: -j$(($(nproc) - 1)) ## Changes Implemented changes to the best of my...

MichaelIspas

NXP backend: Add QAT support for NeutronQuantizer

3

### Summary Adds quantization aware training support for NeutronQuantizer. ### Test plan Dedicated unit tests to be added... cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon

Whisper runner using AOTI native

2

### Summary [PLEASE REMOVE] See [CONTRIBUTING.md's Pull Requests](https://github.com/pytorch/executorch/blob/main/CONTRIBUTING.md#pull-requests) for ExecuTorch PR guidelines. [PLEASE REMOVE] If this PR closes an issue, please add a `Fixes #` line. [PLEASE REMOVE] If this...

larryliu0820