Cache post-lowering ATen graphs to skip decomp on warm compiles. - #4540
Draft
micwill755 wants to merge 1 commit into
Draft
Cache post-lowering ATen graphs to skip decomp on warm compiles.#4540micwill755 wants to merge 1 commit into
micwill755 wants to merge 1 commit into
Conversation
Serialize the live FX node list and state_dict with torch.save so a hit can skip decomposition and post_lowering without retracing generated Python.
github-actions
Bot
added
component: tests
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
GraphModule, keyed from the exported program before decomposition.run_decompositionsandpost_loweringand rebuild the FX graph from a node list +state_dict(torch.save), nottorch.export.saveor FX__reduce__retrace.Test plan
tests/py/dynamo/models/test_lowering_cache.py