[0.9.1][Perf] Optimize the number of rope-related index selections in deepseek. #1614
+56
−22
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
whx-sjtu
changed the title
whx-sjtu
force-pushed
the
ds_rope_opt
branch
5 times, most recently
from
cdae151 to
9621b4d
Compare
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
whx-sjtu
force-pushed
the
ds_rope_opt
branch
5 times, most recently
from
ba98ed2 to
ddea987
Compare
Signed-off-by: whx-sjtu <2952154980@qq.com>
wangxiyuan
changed the title
ganyi1996ppo
approved these changes
Jul 8, 2025
weijinqian0
pushed a commit
to weijinqian0/vllm-ascend
that referenced
this pull request
Jul 9, 2025
… deepseek. (vllm-project#1614) This PR avoids performing index selection of sin/cos cache every layer in deepseek. Signed-off-by: whx-sjtu <2952154980@qq.com> Signed-off-by: weijinqian_v1 <weijinqian@huawei.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Outdated suggestions cannot be applied.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 PR avoids performing index selection of sin/cos cache every layer in deepseek.