Feature Request: Full Gemm operation / node

[mtobin-tdab]

Feature description

Introduction of ONNX Gemm operation conversion https://onnx.ai/onnx/operators/onnx__Gemm.html

Feature motivation

Useful for optimisations

Currently get:

DEBUG onnx_ir::proto_conversion: Converting ONNX node with type "Gemm"    
DEBUG onnx_ir::from_onnx: renaming node "model/..../dense/MatMul_Gemm__6"    
ERROR burn_import::logger: PANIC => panicked at crates/onnx-ir/src/coalesce.rs:55:9:
Full Gemm node not supported yet. 

[antimora]

Thanks for filing. Definitely useful to support Gemm ONNX operator. However, you mentioned it's useful for optimization, what do you mean? So you know, Burn does not have native Gemm operator. So any ONNX Gemm operator translation will be to the Burn APIs. And I don't think we have any plans for Gemm anytime soon, unless @louisfd and @nathanielsimard know better.

[0rvar]

Got stuck on this now while trying to port wake word detection from tflite to Burn. Converted pretrained .tflite models to ONNX, but ModelGen doesn't accept any of them due to Gemm: Full Gemm node not supported yet.

[antimora]

Closing this since GEMM is supported OP via #2841