[xpu]:fix scope new tensor: max weight is unchanged #9641
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
gitliuyf
requested review from
zhupengyang,
hong19860320 and
liyancas
as code owners
|
Thanks for your contribution! |
|
|
|
LGTM |
hong19860320
reviewed
Nov 9, 2022
| @@ -1310,7 +1311,7 @@ class XPUMultiEncoderFuser { | |||
| weight_tensor_vec[0]->Resize({weight_dim1_acc, weight_dims_vec[0][0]}); | |||
| float max_f = | |||
| paddle::lite::xpu::math::FindMaxAbs(weight_qkv_trans.get(), qkv_len); | |||
| auto max_tensor = scope->NewTensor(max_tensor_name); | |||
| auto max_tensor = scope->MutableParent()->NewTensor(max_tensor_name); | |||
There was a problem hiding this comment.
为什么需要在 parent scope 创建一个tensor 呢？是为了解决什么问题呢？
There was a problem hiding this comment.
1、如果是scope->NewTensor()就是从current scope创建，如果是scope->MutableParent()->NewTensor(）就是从root scope创建。
2、因为PaddleLite 现在将权重信息保存在了 root scope中，如果clone多个predictor，会共用一个root scope。
3、需要存放权重才用的MutableParent，如果说你的tensor不需要存放权重，是特征值，是不需要MutableParent的。
newway
pushed a commit
to newway/Paddle-Lite
that referenced
this pull request
Nov 19, 2022
zhupengyang
pushed a commit
that referenced
this pull request
Nov 24, 2022
* [Cherry-Pick][XPU] fixed inplace op mem reuse issue when the previous op is an invalid op (#9562) (#9564) * [XPU] support roformer relative embedding (#9536) * fix sampling_id, fix xpu python whl, fix quant_dequant pass (#9636) * [XPU] support ffn intermediate size M!=4 (#9646) * [xpu] fix scope new tensor, max weight is unchanged (#9641) * [XPU] Fixed the bug in op calib. (#9700) * [XPU] support skip ffn quant in K200 (#9704)
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Outdated suggestions cannot be applied.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.