Rework RotaryEmbedding for dynamic computation #255
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
rsuderman
force-pushed
the
rework_rotary
branch
from
e001434
to
6f86dda
Compare
rsuderman
force-pushed
the
rework_rotary
branch
from
6f86dda
to
01b9172
Compare
archana-ramalingam
approved these changes
Oct 7, 2024
rsuderman
force-pushed
the
rework_rotary
branch
from
01b9172
to
bdf643a
Compare
Some minor changes to the rotary embedding can better support fusion and avoid using a lookup table. Depending on backend one version may provide better overall performance.
rsuderman
force-pushed
the
rework_rotary
branch
from
bdf643a
to
509d662
Compare
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Outdated suggestions cannot be applied.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.
Some minor changes to the rotary embedding can better support fusion and avoid using a lookup table. Depending on backend one version may provide better overall performance.