[Reduce] optimize and unify reduce operator to a single place #311
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
yaoyaoding
approved these changes
Jul 13, 2023
There was a problem hiding this comment.
Thanks @xinli-git ! You are getting more professional in using hidet script :)
vadiklyutiy
pushed a commit
that referenced
this pull request
Jul 22, 2024
…. Fixed (#311) when device is None, `device_from_torch` returns 'cpu' by default. As a result it copies some of the tensors to 'cpu' device. The correct behaviours is to not to move the tensor at all. --------- Co-authored-by: Zhumakhan <nazirzhumakhan@gmail,.com>
vadiklyutiy
pushed a commit
that referenced
this pull request
Jul 23, 2024
…. Fixed (#311) when device is None, `device_from_torch` returns 'cpu' by default. As a result it copies some of the tensors to 'cpu' device. The correct behaviours is to not to move the tensor at all. --------- Co-authored-by: Zhumakhan <nazirzhumakhan@gmail,.com>
vadiklyutiy
pushed a commit
that referenced
this pull request
Dec 26, 2024
…. Fixed (#311) when device is None, `device_from_torch` returns 'cpu' by default. As a result it copies some of the tensors to 'cpu' device. The correct behaviours is to not to move the tensor at all. --------- Co-authored-by: Zhumakhan <nazirzhumakhan@gmail,.com>
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Outdated suggestions cannot be applied.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.
This changes optimizes the reduce operator and unifies both reduce and reduce_f16 into a single class / implementation.
On Llama, 255 tokens (RTX3090)
Before: 6.173s
After: 5.295s
Contribution from reduce:
before: 732ms (13.6% of total)
after: 126ms (2.7% of total)