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Outdated suggestions cannot be applied.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.
added new functions for determining the best available device
added device test and integrated new function into device selection
fixed reference
made sure embed are still on the same device
added log point
added more log points
fixed typo
set W_E to be on the same device
set rms norm to correct device
set device to grouped query attention
Revert "set device to grouped query attention"
This reverts commit 788d355.
This reverts commit e7018c4.
This reverts commit 33f4436.
added debug points
reverted most calls to new function
reverted device list
reverted block loop
reverted cache call
updated move model function to use calculations
fixed remaining device identification issues
restored if
made sure rms norm or on the same device before calculations
added device check before linear attn
checked b_
moved device selection
moved rotary to device
changed device move
rassigned prop
made sure all abstract attention tensors are on the same device
remvoed assignment
updated prop setting
put resid pre on device
removed some log points
ran format
resolved test
removed reassignment
changed device selection point
esnure gated mlp items are on the same device
chagned device direction
Description
Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
Fixes # (issue)
Type of change
Please delete options that are not relevant.
Screenshots
Please attach before and after screenshots of the change if applicable.
Checklist: