Support cuda 64dim #126
Merged
Support cuda 64dim #126
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
|
@qwopqwop200 Hi, can we keep the original cuda kernel for 256dim and make a new one that support 64dim by a simply copy? I think by this way we can maintain the speed for those model who is divisible by 256 and also compatible with those only be divisible by 64 and/or 32 at the cost of little slowdown. |
|
yes. Now it probably works that way. |
PanQiWei
approved these changes
Jun 3, 2023
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Outdated suggestions cannot be applied.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.
Unlike the triton, a slight decrease in speed is to be expected.
But it will make gpt2-xl and falcon work in cuda.