sm小于80的机器支持trt_flash_multihead_matmul_fuse_pass #56492
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
yangjianfengo1
changed the title
yangjianfengo1
changed the title
| @@ -32,10 +32,12 @@ def is_program_valid(self, program_config: ProgramConfig) -> bool: | |||
|
|
|||
There was a problem hiding this comment.
可能需要加一个ut,测试下 q/k/v 输入为两个input(非一个input, 一个weight)的情况
|
Sorry to inform you that 76d8b4f's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually. |
danleifeng
pushed a commit
to danleifeng/Paddle
that referenced
this pull request
Nov 14, 2023
* jingdu duiqi need check * code style * code style * add weight is input * code style * windows ci * fix weight name * rerun ci * re run ci --------- Co-authored-by: yangjianfengo1 <yangjianfeng01.baidu.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Outdated suggestions cannot be applied.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.
PR types
Performance optimization
PR changes
Others
Description
Pcard-71501
sm<80的机器使用memory_efficient_attention支持trt_flash_multihead_matmul_fuse_pass，测试数据如下：