[Unity][MSC][M1.2] Add translate && codegen for tensorflow #15751
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Archermmt
force-pushed
the
msc
branch
7 times, most recently
from
6523300 to
10133d6
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is a pull request for MSC(Multi-System Compile)
RFC: https://discuss.tvm.apache.org/t/rfc-unity-msc-introduction-to-multi-system-compiler/15251/5
Tracking issue: #15233
This is the 2nd part of Milestone 1: Finish RuntimeManager for frameworks
To limit each PR in reviewable size, the Milestone 1 will be split into some steps:
M1.1 Add translate && codegen for torch
M1.2 Add translate && codegen for tensorflow
M1.3 Add codegen for tensorrt
M1.4 Add RuntimeManager and test with relax
M1.5 Add RuntimeManager and test with torch
M1.6 Add RuntimeManager and test with tensorflow
M1.7 Add RuntimeManager and test with tensorrt
Tensorflow GraphDef will be translate to MSCGraph via relay. The codegen for tensorflow follow the same principle with relax codegen, thus generate the model define as well as test.
As mentioned in #15645, MSC enables the relay based features. The test in this PR shows developers how to combine relay.frontend.from_tensorflow and msc.core.codegen.relay_to_relax to "create" a frontend for tensorflow in relax.