Updates tensor offset calculations and formatting #27
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
Adds missing row stride parameters to offset calculations for ZOH and active mask tensors, ensuring proper memory layout access. Improves code readability by standardizing comment formatting and alignment for tensor partition declarations. Removes template parameter from DynamicMask class instantiation, simplifying the interface.
Contributor
There was a problem hiding this comment.
Pull Request Overview
Updates tensor offset calculations by including row stride parameters for ZOH and active mask tensors, standardizes comment formatting for tensor partition declarations, and simplifies the DynamicMask interface by removing an unnecessary template parameter.
- Added
#include "rotary.h"to support rotary embeddings. - Updated
zoh_offsetandactive_mask_offsetcalls to accept row stride arguments. - Removed the
Kernel_traits::kNThreadstemplate parameter fromDynamicMask.
Comments suppressed due to low confidence (2)
csrc/src/flash_fwd_kernel.h:387
- Please update any related documentation or usage examples to remove the second template parameter from
DynamicMask, reflecting the new simplified interface.
FLASH_NAMESPACE::DynamicMask<Is_causal> dynamic_mask(
csrc/src/flash_fwd_kernel.h:22
- [nitpick] Consider placing this new include in the correct alphabetical or grouped order to match the project's include style conventions.
#include "rotary.h"
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Outdated suggestions cannot be applied.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.
Adds missing row stride parameters to offset calculations for ZOH and active mask tensors, ensuring proper memory layout access.
Improves code readability by standardizing comment formatting and alignment for tensor partition declarations.
Removes template parameter from DynamicMask class instantiation, simplifying the interface.