[Deepseek-V2] Fused rope implementation #3105
Merged
+25
−19
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
|
I think the change works. Below in red is the TVM code generated earlier while in green is the TVM code after the change. It is clearly visible that we have stopped doing the reshape + permute + reshape in the newer version. |
annanyapr
force-pushed
the
deepseek-v2-rope-fusion
branch
from
8eac411 to
e3de877
Compare
MasterJH5574
approved these changes
Jan 24, 2025
|
LGTM, thank you @annanyapr! |
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Outdated suggestions cannot be applied.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.
This PR fuses the rope operation with the matrix transposes which we were doing before the rope operation. Have tested the model(after compiling) post the changes.