apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Intel HPU] enable tensor_wise_fp8 (#5324)

Browse Source 
* [Intel HPU] enable tensor_wise_fp8

* update code based on comments

* fix code style issue

* fix bug about RP 5138

* mv kv_cache modifications to HPU backend

* fix FP8 Precision Issues

* fix FP8 Precision Issues

* Add quantization UT

---------

Co-authored-by: yanfeich <yanfei.cheng@intel.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
fmiao2372
2025-12-17 16:45:03 +08:00
committed by GitHub
parent 15f5112ecb
commit 404cf0ece4
17 changed files with 824 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/layers/moe/moe.py
-1
View File
@@ -64,7 +64,6 @@ def get_moe_method():
from fastdeploy.model_executor.layers.backends import HpuMoEMethod
return HpuMoEMethod(None)
# return HpuTensorWiseFP8MoEMethod(None)
elif current_platform.is_maca():
from fastdeploy.model_executor.layers.backends import (