apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-24 01:29:57 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Revert "【New Feature】W4afp8 supports per group quantization (#4272)" (#4854)

Browse Source 
This reverts commit 93fcf7e4ec.
This commit is contained in:
YuBaoku
2025-11-06 17:48:28 +08:00
committed by GitHub
parent 3478d20262
commit 819b2dbbae
26 changed files with 1718 additions and 4378 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/gpu_ops/moe/moe_expert_ffn_wint2.cu
-1
View File
@@ -17,7 +17,6 @@
#include "cutlass/numeric_conversion.h"
#include "group_swiglu_with_masked.h"
#include "helper.h"
#include "moe/fast_hardmard/fast_hardamard_kernel.h"
#include "moe/fused_moe_helper.h"
template <typename DataT,