[BuddyLLaMA] Add GPU lowering example for LLaMA inference. #229
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
SForeKeeper
force-pushed
the
liam-gpu
branch
from
8c4ffa2 to
64184f0
Compare
Co-authored-by: xtayex <[email protected]> Co-authored-by: zhanghb97 <[email protected]>
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Outdated suggestions cannot be applied.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 pull request adds basic instructions for lowering LLaMA MLIR for inference on GPU.
** It needs to be polished after buddy-mlir updates to the latest version of LLVM **
Notice that it doesn't involve any optimization for GPU, hence don't expect a high inference rate.
Optimizations would be implemented gradually using transform dialect, which involves another lowering pipeline.