Add with_output version AppendAttention #3302
Open
+1,334
−94
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
|
Thanks for your contribution! |
yuanlehome
reviewed
Aug 11, 2025
| self.causal, | ||
| self.speculative_method is not None, | ||
| )[0] | ||
| if self.use_output: |
There was a problem hiding this comment.
只修改这个文件还不行，全局搜一下所有调用这个append_attention的地方
fastdeploy/model_executor/layers/attention/ops/append_attention.py
Outdated
Show resolved
Hide resolved
|
麻烦再丰富一下PR描述，说明一下改造的背景、目标 |
lizhenyun01
reviewed
Aug 12, 2025
| @@ -763,3 +1061,64 @@ PD_BUILD_STATIC_OP(append_attention) | |||
| .SetKernelFn(PD_KERNEL(AppendAttention)) | |||
| .SetInferShapeFn(PD_INFER_SHAPE(AppendAttentionInferShape)) | |||
| .SetInferDtypeFn(PD_INFER_DTYPE(AppendAttentionInferDtype)); | |||
|
|
|||
| PD_BUILD_STATIC_OP(append_attention_with_output) | |||
There was a problem hiding this comment.
是否有必要新增算子 直接在append_attn算子上改动是不是更清凉 也不会增加算子复杂度
There was a problem hiding this comment.
这里考虑的是保留了原有的append_attn算子；vllm中也是保留了两种attention算子https://github.com/vllm-project/vllm/blob/ebf7605b0dd58ff5d572d1918e52ca732025eee0/vllm/attention/layer.py#L238
| @@ -85,6 +86,7 @@ def __init__( | |||
| head_dim: int, | |||
| encoder_block_shape_q: int = -1, | |||
| decoder_block_shape_q: int = -1, | |||
| use_output: bool = True, | |||
Comment on lines
+145
to
+146
|
|
||
|
|
There was a problem hiding this comment.
在这里留个TODO，在CudaGraph子图捕获功能开发完之后把 withoutput 和 原版算子合并，降低编译体积
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Outdated suggestions cannot be applied.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.
背景：cudagraph 捕获过程中的张量地址管理
目的：将attention模块的输出前置，便于cudagraph捕获时的张量地址处理