88d03a783f
### What this PR does / why we need it? Refactor `vllm_ascend/ops/fused_moe` to replace scattered MoE business `**kwargs` with typed request objects and explicit stage boundaries. - Prepare, dispatch, MLP, and quant stages now have clearer ownership. - Main MoE path no longer depends on business `kwargs.get(...)` lookups. - Comm and dispatcher interfaces are request-only on the main path. - UTs can assert stage-level fields directly instead of inferring behavior indirectly. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed. --------- Signed-off-by: linfeng-yuan <1102311262@qq.com>
46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
# 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.
|
|
#
|
|
"""Ascend quantization module.
|
|
|
|
This module intentionally avoids eager imports so that importing lightweight
|
|
submodules (for example ``quant_type``) does not trigger heavy registration
|
|
paths and circular imports during startup.
|
|
"""
|
|
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
if TYPE_CHECKING:
|
|
from .compressed_tensors_config import AscendCompressedTensorsConfig
|
|
from .modelslim_config import AscendModelSlimConfig
|
|
|
|
__all__ = [
|
|
"AscendModelSlimConfig",
|
|
"AscendCompressedTensorsConfig",
|
|
]
|
|
|
|
|
|
def __getattr__(name: str) -> Any:
|
|
if name == "AscendModelSlimConfig":
|
|
from .modelslim_config import AscendModelSlimConfig
|
|
|
|
return AscendModelSlimConfig
|
|
if name == "AscendCompressedTensorsConfig":
|
|
from .compressed_tensors_config import AscendCompressedTensorsConfig
|
|
|
|
return AscendCompressedTensorsConfig
|
|
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|