Fix 1383 Llama model on transformers=4.41[WIP] #11280
Merged
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
|
Tested on Max1100 and documented LLama2-7B model metrics on issue-1383, performance metrics of transformers4.41 are similar to 4.38 |
sgwhat
approved these changes
Jun 19, 2024
| if cache_position is not None: | ||
| # for transformers 4.38.0 | ||
| causal_mask = attention_mask[:, :, cache_position, : kv_seq_len] |
There was a problem hiding this comment.
The reason to remove causal_mask here?
There was a problem hiding this comment.
the code is compared to wrong place, did not touch for 4_38
|
|
||
| next_cache = next_decoder_cache if use_cache else None | ||
| if return_legacy_cache: | ||
| next_cache = next_cache.to_legacy_cache() |
There was a problem hiding this comment.
Need to double check if next_decoder_cache is DynamicFP8Cache.
RyuKosei
pushed a commit
to RyuKosei/ipex-llm
that referenced
this pull request
Jul 19, 2024
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Outdated suggestions cannot be applied.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.
Description
add llama_attention_forward_4_41, llama_model_forward_4_41