Rc4 cherry-pick #226
Merged
Rc4 cherry-pick #226
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
### Description This PR adds `repeat_kv` to the model builder for models where `num_attention_heads != num_key_value_heads`. ### Motivation and Context By supporting `repeat_kv`, models where `num_attention_heads != num_key_value_heads` can now run on both CPU and GPU.
yufenglee
approved these changes
Mar 22, 2024
baijumeswani
approved these changes
Mar 22, 2024
For safety. This will ensure the Model object's lifetime matches that of any Generator using it. Same as GeneratorParams and Tokenizer
swap p and k to match generate api functions
set_search_options already supports the functionality, so the extra functions are confusing users since there are multiple ways to do the same thing. set_search_options is also more flexible as it supports all future options without the need for extra APIs.
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Outdated suggestions cannot be applied.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.
No description provided.