99aedaff63
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
|` vllm_ascend/quantization/compressed_tensors/compressed_tensors.py`|
|` vllm_ascend/quantization/quant_config.py`|
|` vllm_ascend/quantization/utils.py`|
|` vllm_ascend/quantization/w4a16.py`|
|` vllm_ascend/quantization/w4a4_flatquant_dynamic.py`|
|` vllm_ascend/quantization/w4a8_dynamic.py`|
|` vllm_ascend/quantization/w8a16.py`|
|` vllm_ascend/quantization/w8a8.py`|
|` vllm_ascend/quantization/w8a8_dynamic.py`|
|` vllm_ascend/quantization/w8a8_pdmix.py`|
|` vllm_ascend/quantization/w8a8mxfp8.py`|
|` vllm_ascend/sample/rejection_sampler.py`|
|` vllm_ascend/sample/sampler.py`|
|` vllm_ascend/worker/block_table.py`|
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
2c24bc6996
Signed-off-by: MrZ20 <2609716663@qq.com>
81 lines
2.8 KiB
Python
81 lines
2.8 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 scheme implementations.
|
|
|
|
This module provides all quantization scheme implementations for Ascend NPU.
|
|
Schemes are automatically registered via the @register_scheme decorator.
|
|
|
|
Usage:
|
|
from vllm_ascend.quantization.methods import get_scheme_class
|
|
|
|
# Get a scheme class by quant_type and layer_type
|
|
scheme_cls = get_scheme_class("W8A8_DYNAMIC", "linear")
|
|
scheme = scheme_cls()
|
|
"""
|
|
|
|
from typing import Any
|
|
|
|
# Import base classes
|
|
from .base import AscendAttentionScheme, AscendLinearScheme, AscendMoEScheme, QuantType
|
|
|
|
# Import registry functions
|
|
from .registry import get_scheme_class, register_scheme
|
|
|
|
# Import all scheme classes for external access
|
|
from .w4a4_flatquant import AscendW4A4FlatQuantDynamicLinearMethod
|
|
from .w4a4_laos_dynamic import AscendW4A4LaosDynamicLinearMethod
|
|
from .w4a8 import AscendW4A8DynamicFusedMoEMethod, AscendW4A8DynamicLinearMethod
|
|
from .w4a16 import AscendW4A16FusedMoEMethod
|
|
from .w8a8_dynamic import AscendW8A8DynamicFusedMoEMethod, AscendW8A8DynamicLinearMethod
|
|
from .w8a8_mxfp8 import AscendW8A8MXFP8DynamicLinearMethod
|
|
from .w8a8_pdmix import AscendW8A8PDMixFusedMoeMethod, AscendW8A8PDMixLinearMethod
|
|
from .w8a8_static import AscendW8A8LinearMethod
|
|
from .w8a16 import AscendW8A16LinearMethod
|
|
|
|
|
|
def is_mx_quant_type(instance: Any) -> bool:
|
|
"""Checks if the quantization method is a microscaling (MX) type."""
|
|
MX_QUANT_TYPES = (AscendW8A8MXFP8DynamicLinearMethod,)
|
|
return isinstance(instance, MX_QUANT_TYPES)
|
|
|
|
|
|
__all__ = [
|
|
# Base classes
|
|
"AscendAttentionScheme",
|
|
"AscendLinearScheme",
|
|
"AscendMoEScheme",
|
|
"QuantType",
|
|
# Registry functions
|
|
"register_scheme",
|
|
"get_scheme_class",
|
|
# Utility functions
|
|
"is_mx_quant_type",
|
|
# Scheme classes
|
|
"AscendW8A8LinearMethod",
|
|
"AscendW8A8DynamicLinearMethod",
|
|
"AscendW8A8DynamicFusedMoEMethod",
|
|
"AscendW8A8MXFP8DynamicLinearMethod",
|
|
"AscendW8A8PDMixLinearMethod",
|
|
"AscendW8A8PDMixFusedMoeMethod",
|
|
"AscendW8A16LinearMethod",
|
|
"AscendW4A8DynamicLinearMethod",
|
|
"AscendW4A8DynamicFusedMoEMethod",
|
|
"AscendW4A16FusedMoEMethod",
|
|
"AscendW4A4FlatQuantDynamicLinearMethod",
|
|
"AscendW4A4LaosDynamicLinearMethod",
|
|
]
|