3217f0d10f
### What this PR does / why we need it? 1. It adds more description for classes in quant_config.py 2. It renames AscendQKVQuantAttentionMethod to AscendKVCacheMethod to align with vLLM naming style. 3. It modifies the process when AscendLinearMethod or AscendKVCacheMethod calls create_weights. ### Does this PR introduce _any_ user-facing change? Yes. When creating weights, now AscendLinearMethod uses get_weight, get_pertensor_param and get_perchannel_param api from linear quant implementation, while AscendKVCacheMethod passes layer into linear quant implementation. ### How was this patch tested? By performing offline inference --------- Signed-off-by: angazenn <zengyanjia@huawei.com> Co-authored-by: angazenn <zengyanjia@huawei.com>
52 lines
1.7 KiB
Python
52 lines
1.7 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.
|
|
#
|
|
|
|
import importlib
|
|
from typing import Any, Dict, List
|
|
|
|
CUSTOMIZED_QUANTIZER_TYPE: List[str] = []
|
|
|
|
|
|
class AscendQuantizer:
|
|
"""An interface to different quantization implementations for ascend hardwares."""
|
|
|
|
@classmethod
|
|
def get_quantizer(cls, quant_config: Dict[str, Any], prefix: str):
|
|
# TODO: Need a param to choose quantization algorithms.
|
|
quantization_algorithm = ''
|
|
|
|
if quantization_algorithm in CUSTOMIZED_QUANTIZER_TYPE:
|
|
return
|
|
|
|
try:
|
|
module = importlib.import_module("mindie_turbo")
|
|
MindIETurboQuantizer = module.MindIETurboQuantizer
|
|
except Exception:
|
|
raise NotImplementedError(
|
|
"There is no available ascend quantizer.")
|
|
|
|
return MindIETurboQuantizer.get_quantizer(quant_config, prefix)
|
|
|
|
def build_linear_method(self):
|
|
raise NotImplementedError
|
|
|
|
def build_moe_method(self):
|
|
raise NotImplementedError
|
|
|
|
def build_attention_method(self):
|
|
raise NotImplementedError
|