EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Revert "[Kernel] add custom moe ops for prefill" (#4806)

Browse Source 
Reverts vllm-project/vllm-ascend#4194 as it broke CI in
https://github.com/vllm-project/vllm-ascend/actions/runs/20030369087/job/57437687382?pr=4791

Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
Mengqing Cao
2025-12-08 23:20:32 +08:00
committed by GitHub
parent 432b861cae
commit 7e70da9fb7
39 changed files with 2 additions and 5562 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
csrc/dispatch_layout/op_kernel/dispatch_layout.cpp
View File

@@ -1,17 +0,0 @@
#include "kernel_operator.h"
#include "dispatch_layout.h"
#include "dispatch_layout_tiling.h"
extern "C" __global__ __aicore__ void dispatch_layout(GM_ADDR topkIdx, GM_ADDR numTokensPerRank, GM_ADDR numTokensPerExpert,
GM_ADDR isTokenInRank, GM_ADDR workspace, GM_ADDR tiling)
{
REGISTER_TILING_DEFAULT(DispatchLayoutTilingData);
GET_TILING_DATA_WITH_STRUCT(DispatchLayoutTilingData, tilingData, tiling);
TPipe pipe;
DispatchLayout<int32_t> op;
op.Init(topkIdx, numTokensPerRank, numTokensPerExpert, isTokenInRank, workspace, &pipe, &tilingData);
op.Process();
}