36 lines
1.2 KiB
Python
36 lines
1.2 KiB
Python
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
||
|
|
# Copyright 2023 The vLLM team.
|
||
|
|
#
|
||
|
|
#
|
||
|
|
# 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.
|
||
|
|
# Adapted from vllm/model_executor/models/qwen3_moe.py
|
||
|
|
# This file is a part of the vllm-ascend project.
|
||
|
|
|
||
|
|
from vllm.model_executor.models.qwen3_moe import Qwen3MoeForCausalLM
|
||
|
|
|
||
|
|
|
||
|
|
class CustomQwen3MoeForCausalLM(Qwen3MoeForCausalLM):
|
||
|
|
packed_modules_mapping = {
|
||
|
|
"qkv_proj": [
|
||
|
|
"q_proj",
|
||
|
|
"k_proj",
|
||
|
|
"v_proj",
|
||
|
|
],
|
||
|
|
"gate_up_proj": [
|
||
|
|
"gate_proj",
|
||
|
|
"up_proj",
|
||
|
|
],
|
||
|
|
"experts":
|
||
|
|
["experts.0.gate_proj", "experts.0.up_proj", "experts.0.down_proj"],
|
||
|
|
}
|