[ONNX][TORCH] Add Onnx->Linalg lowering for RotaryEmbedding Op

[vivekkhandelwal1]

This commit adds the Onnx->Linalg lowering for Onnx's RotaryEmbedding op (ref: https://github.com/microsoft/onnxruntime/blob/main/docs/ContribOperators.md#commicrosoftrotaryembedding) by registering a customized torch op named OnnxVariantAtenRotaryEmbeddingOp. This is done so that the Onnx's RotaryEmbedding op can be lowered to this op and this op can be lowered from Torch->Linalg.

The lowering has been adopted from the OnnxRuntime. Files for references:
1.) https://github.com/microsoft/onnxruntime/blob/e1e3f623f61816008e79dddc91a51ffe7f0ff5cf/onnxruntime/contrib_ops/cpu/bert/rotary_embedding.cc#L47-L93
2.) https://github.com/microsoft/onnxruntime/blob/94c69f55d480cb4a8dcbc161d29ef3acca9392a7/onnxruntime/contrib_ops/cpu/bert/rotary_embedding_helper.h

Signed-off-by: Vivek Khandelwal [email protected]

[AmosLewis]

We need a test in https://github.com/nod-ai/SHARK-TestSuite/tree/main/alt_e2eshark/onnx_tests/operators to verify the numeric before merge

[vivekkhandelwal1]

We need a test in https://github.com/nod-ai/SHARK-TestSuite/tree/main/alt_e2eshark/onnx_tests/operators to verify the numeric before merge

Actually, the test in SHARK-Testsuite is not working since the op comes from "com.microsoft" domain. Alhtough, I have verified the e2e correctness of lowering by manually generating the IR and then compiling and executing it with the IREE.

[zjgarvey]

A few small comments. I haven't double checked that the implementation is correct.