[GPTNeoX] Faster rotary embedding for GPTNeoX (based on llama changes)
#25830
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
|
The documentation is not available anymore as the PR was closed or merged. |
ArthurZucker
changed the title
GPTNeoX] Faster rotary embedding for GPTNeoX (based on llama changes)
amyeroberts
reviewed
Aug 31, 2023
gante
approved these changes
Aug 31, 2023
|
cc @StellaAthena FYI, this PR should greatly speed up the ROPE embeddings of the GPTNeoX model, similarly to how it was done for the LLaMa model. Let us know if you want to review/have any comments! |
LysandreJik
approved these changes
Sep 18, 2023
|
cc @Narsil as this touches buffers that will no longer be persistent, will wait for you in case this is conflicting with TGI? |
…rs into improve-gpt-neox
…rs; branch 'main' of github.com:huggingface/transformers into improve-gpt-neox
5 tasks
blbadger
pushed a commit
to blbadger/transformers
that referenced
this pull request
Nov 8, 2023
…es) (huggingface#25830) * Faster rotary embedding for GPTNeoX * there might be un-necessary moves from device * fixup * fix dtype issue * add copied from statements * fox copies * oupsy * add copied from Llama for scaled ones as well * fixup * fix * fix copies
EduardoPach
pushed a commit
to EduardoPach/transformers
that referenced
this pull request
Nov 18, 2023
…es) (huggingface#25830) * Faster rotary embedding for GPTNeoX * there might be un-necessary moves from device * fixup * fix dtype issue * add copied from statements * fox copies * oupsy * add copied from Llama for scaled ones as well * fixup * fix * fix copies
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Outdated suggestions cannot be applied.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.
What does this PR do?
Fixes #25813 which indicates that ROPE is slow. It's a follow up of #22785, were ROPE was improved for Llama model.