-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add a inplace concat custom op based on CUDA VMM API #9126
Draft
lszxb
wants to merge
12
commits into
PaddlePaddle:develop
Choose a base branch
from
lszxb:add_vtensor_op
base: develop
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
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
… loop, avoiding redundant kv cache copy
Thanks for your contribution! |
21 tasks
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## develop #9126 +/- ##
===========================================
- Coverage 53.26% 53.26% -0.01%
===========================================
Files 652 652
Lines 105587 105588 +1
===========================================
Hits 56237 56237
- Misses 49350 49351 +1 ☔ View full report in Codecov by Sentry. |
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Outdated suggestions cannot be applied.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.
PR types
Performance optimization
PR changes
Others
Description
这一PR尝试为当前的大模型推理过程增加基于CUDA VMM API的inplace concat支持(原理类似于vAttention),从而避免在每一个解码步都复制一次整个KV Cache。
该功能暂时只实现了自定义算子,未来还需要增加相关的pass以自动适配其他模型。
目前这一PR在llama模型上应用了这一方案,在3072 input+1024 output的情况下大约有10%的提升。
目前主要的思路是:
vtensor_reserve_one_token自定义算子的语义大致如下:
目前可能存在的问题: