mirror of
https://github.com/huggingface/diffusers.git
synced 2026-01-29 07:22:12 +03:00
updates
This commit is contained in:
@@ -21,6 +21,7 @@ from typing import Dict, Optional, Union
|
||||
|
||||
from .bitsandbytes import BnB4BitDiffusersQuantizer, BnB8BitDiffusersQuantizer
|
||||
from .gguf import GGUFQuantizer
|
||||
from .higgs import HiggsQuantizer
|
||||
from .quantization_config import (
|
||||
BitsAndBytesConfig,
|
||||
GGUFQuantizationConfig,
|
||||
@@ -40,7 +41,7 @@ AUTO_QUANTIZER_MAPPING = {
|
||||
"gguf": GGUFQuantizer,
|
||||
"quanto": QuantoQuantizer,
|
||||
"torchao": TorchAoHfQuantizer,
|
||||
"higgs": 1,
|
||||
"higgs": HiggsQuantizer,
|
||||
}
|
||||
|
||||
AUTO_QUANTIZATION_CONFIG_MAPPING = {
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
from .higgs_quantizer import HiggsQuantizer
|
||||
|
||||
@@ -35,7 +35,7 @@ if is_torch_available():
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class HiggsHfQuantizer(DiffusersQuantizer):
|
||||
class HiggsQuantizer(DiffusersQuantizer):
|
||||
"""
|
||||
Quantizer of the HIGGS method. Enables the loading of prequantized models and in-flight quantization of
|
||||
full-precision models.
|
||||
|
||||
@@ -46,6 +46,7 @@ class QuantizationMethod(str, Enum):
|
||||
GGUF = "gguf"
|
||||
TORCHAO = "torchao"
|
||||
QUANTO = "quanto"
|
||||
HIGGS = "higgs"
|
||||
|
||||
|
||||
if is_torchao_available():
|
||||
|
||||
Reference in New Issue
Block a user