llama : replace (permute + reshape + view_1d) with (view_3d) #2538
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
KerfuffleV2
approved these changes
Aug 17, 2023
Contributor
KerfuffleV2
left a comment
KerfuffleV2
left a comment
There was a problem hiding this comment.
Not sure how much this approval is worth, but I tested inference on CPU and GPU (with the ROCM pull) and perplexity only on GPU. As far as I can see this does not affect the result at all: same perplexity, identical generation with a specific seed.
It also doesn't appear to have any noticeable effect on performance.
Member
Author
|
Thanks for confirming. Yes, this should just reduce the number of nodes and make the code a tiny bit more clear - nothing dramatic. |
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Outdated suggestions cannot be applied.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.
Simplify the compute graph