[PaddleInference] support ptq and cachekv_quant in BlockMultiHeadAttention op #59951
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! |
RichardWooSJTU
force-pushed
the
cache_kv_quant
branch
from
e16a233 to
121733e
Compare
RichardWooSJTU
changed the title
RichardWooSJTU
force-pushed
the
cache_kv_quant
branch
from
3b56fd5 to
2e69d09
Compare
| "be less than [%d] and greater than or equal to 0, but received [%d]", | ||
| vocab_size, | ||
| id); | ||
| // PADDLE_ENFORCE( |
There was a problem hiding this comment.
目前多轮会报错在这里 报错不符合预期 还在找作者debug
MARD1NO
approved these changes
Dec 14, 2023
| "be less than [%d] and greater than or equal to 0, but received [%d]", | ||
| vocab_size, | ||
| id); | ||
| // PADDLE_ENFORCE( |
There was a problem hiding this comment.
目前多轮会报错在这里 报错不符合预期 还在找作者debug
Aurelius84
approved these changes
Dec 15, 2023
vivienfanghuagood
approved these changes
Dec 15, 2023
heavengate
approved these changes
Dec 15, 2023
jeff41404
reviewed
Dec 15, 2023
Comment on lines
+33
to
+40
| cache_k_quant_scales=None, | ||
| cache_v_quant_scales=None, | ||
| cache_k_dequant_scales=None, | ||
| cache_v_dequant_scales=None, | ||
| qkv_out_scale=None, | ||
| qkv_bias=None, | ||
| out_shift=None, | ||
| out_smooth=None, |
There was a problem hiding this comment.
The newly added parameters, such as cache_k_quant_scales, need to be described in docstring of section Args below
There was a problem hiding this comment.
Normally, the added parameters should be added at the end to ensure compatibility
There was a problem hiding this comment.
This will be added in next PR.
jeff41404
approved these changes
Dec 15, 2023
raindrops2sea
approved these changes
Dec 15, 2023
RichardWooSJTU
added a commit
to RichardWooSJTU/Paddle
that referenced
this pull request
Dec 15, 2023
…ntion op (PaddlePaddle#59951) * support cachekv_quant in blha --------- Co-authored-by: Wanglongzhi2001 <[email protected]>
RichardWooSJTU
added a commit
to RichardWooSJTU/Paddle
that referenced
this pull request
Dec 15, 2023
…ntion op (PaddlePaddle#59951) * support cachekv_quant in blha --------- Co-authored-by: Wanglongzhi2001 <[email protected]>
raindrops2sea
pushed a commit
that referenced
this pull request
Dec 18, 2023
…ntion op (#59951) (#60073) * support cachekv_quant in blha --------- Co-authored-by: Wanglongzhi2001 <[email protected]>
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
For block attention
Pcard-71502