Make example generation work when the model is torch.compile-d #78
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
IggShaman
force-pushed
the
igshevchenko/make_model_compile_compatible_with_example_generation
branch
from
dc054e5
to
b50b3da
Compare
IggShaman
force-pushed
the
igshevchenko/make_model_compile_compatible_with_example_generation
branch
from
b50b3da
to
ea398de
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Outdated suggestions cannot be applied.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.
Andrej mentions this issue a couple of times in the video. Apparently, when a model is compiled, it will fix its input and output tensor sizes. The training regime works with inputs of shape (B, T), currently configured to (64, 1024). Example generation works with input tensors of shapes (4, 8) ... (4, 32).
A simple workaround here is to pad example generation tensors to the (B, T) shape, and ignore extra rows. The same workaround applies to the hellaswag eval.
Unfortunately, this increases the computation time linearly to both the B and T, so quadratically overall.