[Model] Llama model implementation in hidet#243
Merged
yaoyaoding merged 42 commits intohidet-org:mainfrom Jun 7, 2023
Merged
Conversation
yaoyaoding
reviewed
May 26, 2023
Member
yaoyaoding
left a comment
There was a problem hiding this comment.
Hi @Aalanli,
I hvae taken a rough look and it looks good. One minor concern is that whether we need to add the matmul and cat under the hidet.graph.tensor namespace. I still prefer we directly use the hidet.ops.matmul and hidet.ops.concat instead.
Member
|
By the way, I have refactored the structure of |
Hidet compiled model does not check input types are correct
Contributor
Author
|
Just waiting for the graph fusion failure to be addressed, currently generating prompts with no graph optimization works as expected. |
added 6 commits
June 2, 2023 16:29
Contributor
Author
|
Waiting for PR#268 |
Member
|
Thanks @Aalanli ! |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Preliminary llama model implementation in hidet.
Changed some imports to make the structure more like torch for convenience.
Verified model loading on a small synthetic model. However, I cannot verify the actual model loading due to memory constraints.
Inference script not included, working on auto translator to move the huggingface infrastructure over from torch.