Welcome to discuss TensorRT Dialect

MLIR
1

Hi, recently, my colleagues and I have use torch-mlir as front-end tool to convert Huggingface’s Bert model into TensorRT model.
We added some graph-opt passes(base on Torch Dialect) by using graph optimization tool of MLIR, and then used them together with TensorRT api and some customized TensorRT plugins, which achieved better performance than “torch-mlir + iree” and ONNX-TensorRT.
Here, I have two questions:

  1. Will the Mlir community have any plans to support TensorRT Dialect in the future?
  2. If we design a TensorRT Dialect, Is it necessary? Or will it be valuable? Are there any requirement if we want to contribute it to torch-mlir in the future?
2

Maybe worth posting in #projects-that-want-to-become-official-llvm-projects:torch-mlir . Also the torch-mlir discord is very active. @_sean_silva

1 Like
3

(Moved into torch-mlir FYI)

4

Hey folks, can you move this into the main MLIR channel? This discussion is mainly about TensorRT dialect. I actually moved this from a Torch-MLIR issue to the main MLIR discourse for that reason (original issue: About TensorRT Dialect · Issue #1239 · llvm/torch-mlir · GitHub)

5

OK，move it。Thanks!

6

@mehdi_amini can you move it back to MLIR category?

1 Like