search

tenstorrent / tt-forge-fe

The TT-Forge FE is a graph compiler designed to optimize and transform computational graphs for deep learning models, enhancing their performance and efficiency.
https://docs.tenstorrent.com/tt-forge-fe/
Apache License 2.0
20 stars 3 forks source link

[ViT] - Add specific op tests #755

Open vkovinicTT opened 9 hours ago

vkovinicTT commented 9 hours ago

Summary

To confirm that each op individually works for the ViT model, we need to add a set of op tests that are specific to this ViT model.

To do so, here are a few hints:

  1. Print unique ops appearing in ViT.
    • To do so, use this feature
  2. For each unique op (and related input shape, attribute, etc.) create an e2e op test
    • The recommendation is to keep these model-related op tests as part of the model directory. E.g. forge/test/mlir/vit/ops/*
  3. Make sure to run e2e tests as further as possible
    • To make this possible, you can use compile depth (e.g. compiler_cfg.compile_depth = forge.CompileDepth.SPLIT_GRAPH)