add flash_attention on model chatglm_v2 #9296
Merged
Conversation
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
|
Thanks for your contribution! |
|
huxinye seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #9296 +/- ##
===========================================
- Coverage 53.11% 52.92% -0.19%
===========================================
Files 665 660 -5
Lines 109041 106857 -2184
===========================================
- Hits 57918 56555 -1363
+ Misses 51123 50302 -821 ☔ View full report in Codecov by Sentry. |
lugimzzz
reviewed
Oct 22, 2024
| self.hidden_size_per_attention_head, | ||
| ] | ||
| ) | ||
|
|
Contributor
There was a problem hiding this comment.
这一段reshape的逻辑不应该加在这里，破坏了原有的非fa2的逻辑。而且下面还有支持sequence_parallel的逻辑会重新reshape
| ) | ||
| version_check = False | ||
| if self.config.use_flash_attention and version_check: | ||
| attention_mask = attention_mask |
Contributor
There was a problem hiding this comment.
对qkv的reshape可以放在if config.use_flash_attention下面，并且需要考虑sequence parallel
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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.
PR types
others
PR changes
models
Description
add flash_attention on model chatglm_v2