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

51
csrc/dispatch_layout/op_host/dispatch_layout.cpp
View File

@@ -1,51 +0,0 @@
#include "register/op_def_registry.h"
namespace ops {
class DispatchLayout : public OpDef {
public:
explicit DispatchLayout(const char *name) : OpDef(name)
{
this->Input("topkIdx")
.ParamType(REQUIRED)
.DataType({ge::DT_INT64})
.Format({ge::FORMAT_ND})
.UnknownShapeFormat({ge::FORMAT_ND});
this->Attr("num_tokens").Int();
this->Attr("num_ranks").Int();
this->Attr("num_experts").Int();
this->Attr("num_topk").Int();
this->Output("numTokensPerRank")
.ParamType(REQUIRED)
.DataType({ge::DT_INT32})
.Format({ge::FORMAT_ND})
.UnknownShapeFormat({ge::FORMAT_ND});
this->Output("numTokensPerExpert")
.ParamType(REQUIRED)
.DataType({ge::DT_INT32})
.Format({ge::FORMAT_ND})
.UnknownShapeFormat({ge::FORMAT_ND});
this->Output("isTokenInRank")
.ParamType(REQUIRED)
.DataType({ge::DT_INT32})
.Format({ge::FORMAT_ND})
.UnknownShapeFormat({ge::FORMAT_ND});
OpAICoreConfig aicore_config;
aicore_config.DynamicCompileStaticFlag(true)
.DynamicFormatFlag(true)
.DynamicRankSupportFlag(true)
.DynamicShapeSupportFlag(true)
.NeedCheckSupportFlag(false)
.PrecisionReduceFlag(true)
.ExtendCfgInfo("aclnnSupport.value", "support_aclnn")
.ExtendCfgInfo("jitCompile.flag", "static_true")
.ExtendCfgInfo("multiKernelSupportDynamicGraph.value", "multi_kernel");
this->AICore().AddConfig("ascend910_93", aicore_config);
}
};
OP_ADD(DispatchLayout);
} // namespace ops