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

84
csrc/notify_dispatch/op_host/aclnn_notify_dispatch.cpp
View File

@@ -1,84 +0,0 @@
#include <string.h>
#include "graph/types.h"
#include "aclnn_notify_dispatch.h"
extern void NnopbaseOpLogE(const aclnnStatus code, const char *const expr);
#ifdef __cplusplus
extern "C" {
#endif
enum NnopbaseHcclServerType {
NNOPBASE_HCCL_SERVER_TYPE_AICPU = 0,
NNOPBASE_HCCL_SERVER_TYPE_MTE,
NNOPBASE_HCCL_SERVER_TYPE_END
};
extern "C" void __attribute__((weak)) NnopbaseSetHcclServerType(void *executor, NnopbaseHcclServerType sType);
extern aclnnStatus aclnnInnerNotifyDispatchGetWorkspaceSize(
const aclTensor *sendData,
const aclTensor *tokenPerExpertData,
int64_t sendCount,
int64_t numTokens,
char *commGroup,
int64_t rankSize,
int64_t rankId,
int64_t localRankSize,
int64_t localRankId,
const aclTensor *sendDataOffset,
const aclTensor *recvData,
uint64_t *workspaceSize,
aclOpExecutor **executor);
extern aclnnStatus aclnnInnerNotifyDispatch(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream);
aclnnStatus aclnnNotifyDispatchGetWorkspaceSize(
const aclTensor *sendData,
const aclTensor *tokenPerExpertData,
int64_t sendCount,
int64_t numTokens,
char *commGroup,
int64_t rankSize,
int64_t rankId,
int64_t localRankSize,
int64_t localRankId,
const aclTensor *sendDataOffset,
const aclTensor *recvData,
uint64_t *workspaceSize,
aclOpExecutor **executor)
{
return aclnnInnerNotifyDispatchGetWorkspaceSize(
sendData,
tokenPerExpertData,
sendCount,
numTokens,
commGroup,
rankSize,
rankId,
localRankSize,
localRankId,
sendDataOffset,
recvData,
workspaceSize,
executor);
}
aclnnStatus aclnnNotifyDispatch(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)
{
if (NnopbaseSetHcclServerType) {
NnopbaseSetHcclServerType(executor, NNOPBASE_HCCL_SERVER_TYPE_MTE);
}
return aclnnInnerNotifyDispatch(workspace, workspaceSize, executor, stream);
}
#ifdef __cplusplus
}
#endif