Mark input tokens to routed experts as dynamic to avoid a recompile #2007
Conversation
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
stack-info: PR: #2007, branch: xmfan/stack/3
xmfan
requested review from
fegin,
tianyu-l,
wconstab and
wwwjn
as code owners
meta-cla
bot
added
the
CLA Signed
Contributor
|
the fix for #1971 requires using PyTorch nightly as of a few days ago ( |
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Outdated suggestions cannot be applied.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.
Stacked PRs:
Mark input tokens to routed experts as dynamic to avoid a recompile
This saves 1 recompile, and you can see the input tokens are dynamic from the first graph compiled:
I verified that this also fixes the AC recompile issue of: #1971. But I'm keeping
torch._C._dynamo.eval_frame._set_lru_cache(False), as there could be other recompile reasons popping up.