File size: 1,803 Bytes
fb42d3e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
# Copyright 2025 The HuggingFace Team. 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.
"FP-Quant integration file"
from ..utils import (
is_fp_quant_available,
)
if is_fp_quant_available():
from fp_quant import FPQuantConfig as FPQuantLinearConfig
from fp_quant import FPQuantDtype
from transformers.utils.quantization_config import FPQuantConfig
def adapt_fp_quant_config(config: FPQuantConfig):
if config.forward_dtype == "mxfp4":
forward_dtype = FPQuantDtype.MXFP4
elif config.forward_dtype == "nvfp4":
forward_dtype = FPQuantDtype.NVFP4
else:
raise ValueError(f"Unsupported forward dtype: {config.forward_dtype}")
if config.backward_dtype == "bf16":
backward_dtype = FPQuantDtype.BF16
else:
raise ValueError(f"Unsupported backward dtype: {config.backward_dtype}")
return FPQuantLinearConfig(
forward_dtype=forward_dtype,
forward_method=config.forward_method,
backward_dtype=backward_dtype,
store_master_weights=config.store_master_weights,
hadamard_group_size=config.hadamard_group_size,
pseudoquantization=config.pseudoquantization,
transform_init=config.transform_init,
modules_to_not_convert=config.modules_to_not_convert,
)
|