StaticLLMPipeline: Optimize V-tensors layout by Anatolii Talamanov #1232
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
github-actions
bot
added
category: LLM
Wovchena
approved these changes
Nov 19, 2024
dmatveev
reviewed
Nov 19, 2024
| // (8) Compile both model | ||
| // (6) Apply opt layout if applicable | ||
| // NB: Try to apply opt transpose only for Llama-2-7b-chat-hf model | ||
| if ( model_desc.name_or_path == "meta-llama/Llama-2-7b-chat-hf" || |
There was a problem hiding this comment.
I think both lhs & rhs in == should be lowercased first to make comparison more robust
There was a problem hiding this comment.
Will create a ticket for this!
There was a problem hiding this comment.
do we need hardcode for specific model? is not model_desc.type == "llama" enough ?
There was a problem hiding this comment.
@ilya-lavrenov we're not confident (yet) if it will work for other llama versions. @TolyaTalamanov will generalize this change as he gets back from vacation
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Outdated suggestions cannot be applied.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.
Retargeted #1177 to master, added
port to LTSlabel.Ticket: