add quant_linear #57852
Merged
add quant_linear #57852
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! |
| phi::QuantLinearKernel, | ||
| float, | ||
| double, | ||
| phi::dtype::float16) {} |
| int in_num_col_dims, | ||
| const std::string& activation_type, | ||
| bool padding_weights, | ||
| bool is_quant, |
There was a problem hiding this comment.
算子名称已经是QuantLinear 这个参数是否有必要保留
There was a problem hiding this comment.
那后续删掉这个参数，算子改为只支持quant。
麻烦在PR描述里写上op的运行方式以及应用场景吧～ |
| case 4: | ||
| QuantKernelWithVecSize<<<grid, block, 0, stream>>>( | ||
| input, | ||
| (char4*)output, // NOLINT |
There was a problem hiding this comment.
是不是还是用reinterpret_cast好一些
| float quant_max_bound, | ||
| float quant_min_bound, | ||
| DenseTensor* y) { | ||
| bool with_relu = activation_type == "relu" ? true : false; |
There was a problem hiding this comment.
对于给入非relu的激活, 好像没有做处理?
There was a problem hiding this comment.
目前是只支持relu激活，在InferMeta里对activation_type 非relu的情况做了检查。
| be created according to ParamAttr. For detailed information, please refer | ||
| to :attr:`paddle.ParamAttr`. The default value is None and the bias will be | ||
| initialized to zero. | ||
| activation (str, optional): Activation to be applied to the output of |
There was a problem hiding this comment.
文档这里可能需要写明给出已支持的activation方法列表
wanghuancoder
approved these changes
Oct 30, 2023
XiaoguangHu01
approved these changes
Oct 31, 2023
heavengate
approved these changes
Oct 31, 2023
zeroRains
pushed a commit
to zeroRains/Paddle
that referenced
this pull request
Nov 8, 2023
* move fc to phi
|
hi, @YSF-A
|
danleifeng
pushed a commit
to danleifeng/Paddle
that referenced
this pull request
Nov 14, 2023
* move fc to phi
Closed
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
New features
PR changes
OPs
Description
add quant_linear
输入input、bias与in8的w，以及quant scale、round_type、max_bound、min_bound等量化相关的参数，可以计算获得output。其中，input量化为layer_wise，w量化为channel_wise。
应用场景是用于需要量化的Linear的场景。