[Inference] Append attn FP8 quant #9328
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
|
Thanks for your contribution! |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #9328 +/- ##
===========================================
+ Coverage 52.24% 52.97% +0.72%
===========================================
Files 673 673
Lines 109100 107355 -1745
===========================================
- Hits 56998 56868 -130
+ Misses 52102 50487 -1615 ☔ View full report in Codecov by Sentry. |
yuanlehome
reviewed
Oct 30, 2024
Comment on lines
+2873
to
+2874
| def compute_activation(self, ffn1_out, i): | ||
| return ffn1_out |
There was a problem hiding this comment.
使用自定义算子实现的cutlass版本的FP8 dual gemm融合了act；
使用Paddle实现的cublaslt的FP8 gemm在compute_ffn1函数内计算了act，所以继承的这个方法置空就可以了；
yuanlehome
reviewed
Oct 30, 2024
| @@ -321,6 +323,7 @@ __global__ void multi_query_append_attention_kernel( | |||
| smooth_weight, | |||
| q_base_seq_id_this_block, | |||
| q_head_idx, | |||
| quant_max_bound,quant_min_bound, | |||
yuanlehome
previously approved these changes
Oct 30, 2024
…nto append_attn_fp8_quant
yuanlehome
approved these changes
Nov 4, 2024
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Outdated suggestions cannot be applied.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
Others
PR changes
Others
Description
append attn支持FP8 e4m3量化；
编译自定义算子时，自动生成FP8 cutlass gemm，并增加FP8 cutlass GEMM默认配置；
将FP8组网统一到FusedBlockMultiTransformer，方便后续维护；