cuda : fix RoPE after #2268 #3897
Merged
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
ggerganov
approved these changes
Nov 2, 2023
|
We have an assert for Line 6564 in 2fffa0d |
olexiyb
pushed a commit
to Sanctum-AI/llama.cpp
that referenced
this pull request
Nov 23, 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Outdated suggestions cannot be applied.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.
Follow-up to #2268
ref: #2268 (comment)
I had meant to test this change, but I had evidently forgotten the
-nglparameter. Then CI passed and I thought I was in the clear to merge. Oops.Integer division semantics had slipped my mind because I've been writing too much python. And apparently
rowdoes not mean what I thought it did in this kernel. I don't think figuring out the details ofne00 != n_dimsis worth the trouble if we don't have a model to actually test with, and I think the comment makes it sufficiently clear what is going on.