weight_quantize api support gpu #59090
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! |
MARD1NO
approved these changes
Nov 21, 2023
| @@ -30,14 +30,14 @@ | |||
|
|
|||
| #pragma once | |||
|
|
|||
| #include "paddle/phi/backends/cpu/cpu_context.h" | |||
| // #include "paddle/phi/backends/cpu/cpu_context.h" | |||
yuanlehome
previously approved these changes
Nov 21, 2023
wwbitejotunn
force-pushed
the
develop_quanted_weight_gpu
branch
from
2166380
to
1ac2c63
Compare
MARD1NO
approved these changes
Nov 23, 2023
yuanlehome
changed the title
SecretXV
pushed a commit
to SecretXV/Paddle
that referenced
this pull request
Nov 28, 2023
* weight quant gpu wint8 * fix scale type of weight ony quant * fix cpu quant weight * update * float scale for weight-only8 gpu quant * fix infermeta * fix include * add sm70 * fixup and andd sm70 * code_style fix
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Outdated suggestions cannot be applied.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
Function optimization
PR changes
OPs
Description
Add quanted weight gpu kernel for weight only int8 to speed up the model convert. sm70 premute kernel is contributed by @MARD1NO
Pcard-71502