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

Refactor the ops PyTorch adapter，cleanup for csrc/torch_binding.cpp (#6732)

Browse Source 
### What this PR does / why we need it?
Refactor the ops PyTorch adapter，cleanup for csrc/torch_binding.cpp,
more details see
https://github.com/vllm-project/vllm-ascend/issues/6486

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
install the new package to test the new modification, here is the
result:


- vLLM version: v0.15.0
- vLLM main:
9562912cea

---------

Signed-off-by: liziyu <liziyu16@huawei.com>
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Signed-off-by: luomin2005 <luomin2005@huawei.com>
Co-authored-by: liziyu <56102866+liziyu179@users.noreply.github.com>
Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com>
This commit is contained in:
luomin2005
2026-02-24 09:12:43 +08:00
committed by GitHub
parent f0caeeadcb
commit f41eeeb11e
15 changed files with 1037 additions and 735 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
csrc/dispatch_ffn_combine/dispatch_ffn_combine_torch_adpt.h Normal file
View File

@@ -0,0 +1,65 @@
/*
* Copyright (c) Huawei Technologies Co., Ltd. 2026. All rights reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#ifndef DISPATCH_FFN_COMBINE_TORCH_ADPT_H
#define DISPATCH_FFN_COMBINE_TORCH_ADPT_H
namespace vllm_ascend {
std::tuple<at::Tensor&, at::Tensor&> dispatch_ffn_combine(
const at::Tensor& x,
const at::TensorList& weight1,
const at::TensorList& weight2,
const at::Tensor& expert_idx,
const at::TensorList& scale1,
const at::TensorList& scale2,
const at::Tensor& probs,
c10::string_view group,
int64_t max_output_size,
at::Tensor& out,
at::Tensor& expert_token_nums
) {
char *group_ep_ptr = const_cast<char *>(group.data());
bool is_int8 = weight1[0].dtype() == at::kChar;
if (is_int8) {
EXEC_NPU_CMD(aclnnDispatchFFNCombine,
x,
weight1,
weight2,
expert_idx,
scale1,
scale2,
probs,
group_ep_ptr,
max_output_size,
out,
expert_token_nums);
} else {
EXEC_NPU_CMD(aclnnDispatchFFNCombineBF16,
x,
weight1,
weight2,
expert_idx,
scale1,
scale2,
probs,
group_ep_ptr,
max_output_size,
out,
expert_token_nums);
}
return {out, expert_token_nums};
}
}
#endif