nod-ai / SHARK-ModelDev

Unified compiler/runtime for interfacing with PyTorch Dynamo.
Apache License 2.0
95 stars 48 forks source link

Turbine Camp #828

Open pdhirajkumarprasad opened 2 months ago

pdhirajkumarprasad commented 2 months ago

Introduction

This page provides information on implementing complete support of ONNX operators in Shark/IREE front-end. This effort is a part of overall ONNX quality improvement tracked by #812

Pre-requisites

Development Workspace

Create a fork of https://github.com/llvm/torch-mlir and follow build instructions to build a clone of your fork and push changes using Pull Requests

Guidelines

Contact:

Onnx Ops( Known missing features)

Onnx Ops( Known Quality Issues)

Other tasks:

https://github.com/llvm/torch-mlir/issues/3796

knwng commented 1 month ago

Seems LSTM also has quality issue. But it seems the testcases themselves are buggy(wrong # of inputs & outputs). Besides, RNN only has 1 testcase rn. I'm afraid it can't cover all the corner cases.

vivekkhandelwal1 commented 1 month ago

Seems LSTM also has quality issue. But it seems the testcases themselves are buggy(wrong # of inputs & outputs). Besides, RNN only has 1 testcase rn. I'm afraid it can't cover all the corner cases.

Yeah, the issue for LSTM is already opened here https://github.com/nod-ai/SHARK-ModelDev/issues/315.