[Layers] Add qwenRope support for Qwen1.0 in CB mode #449
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
abenmao
force-pushed
the
layers/rope/qwen1
branch
from
4e167cd
to
5446a57
Compare
pujiang2018
approved these changes
Jun 17, 2024
|
|
||
| #pragma omp parallel for collapse(2) | ||
| for (int head = 0; head < heads; ++head) { | ||
| for (int seq = 0; seq < totSeqLen; ++seq) { |
There was a problem hiding this comment.
For next step, considering first token, should we swap the 2 loops to make each thread accessing contiguous memory? may deserve to test such implementation.
OK for current version.
|
I think this kernel APIs on continuous batching version and on continuous batching version are the same. Next step. we could merge two into one kernel API. |
Yes, maybe we can remove the older version in the next step. |
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Outdated suggestions cannot be applied.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.
No description provided.