探索 Diffusers 中的量化後端

import torch
from diffusers import FluxPipeline
from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
from diffusers.quantizers import PipelineQuantizationConfig
from transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig

model_id = "black-forest-labs/FLUX.1-dev"

pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
        "transformer": DiffusersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
        "text_encoder_2": TransformersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
    }
)

pipe = FluxPipeline.from_pretrained(
    model_id,
    quantization_config=pipeline_quant_config,
    torch_dtype=torch.bfloat16
)
pipe.to("cuda")

prompt = "Baroque style, a lavish palace interior with ornate gilded ceilings, intricate tapestries, and dramatic lighting over a grand staircase."
pipe_kwargs = {
    "prompt": prompt,
    "height": 1024,
    "width": 1024,
    "guidance_scale": 3.5,
    "num_inference_steps": 50,
    "max_sequence_length": 512,
}


print(f"Pipeline memory usage: {torch.cuda.max_memory_reserved() / 1024**3:.3f} GB")

image = pipe(
    **pipe_kwargs, generator=torch.manual_seed(0),
).images[0]

print(f"Pipeline memory usage: {torch.cuda.max_memory_reserved() / 1024**3:.3f} GB")

image.save("flux-dev_bnb_4bit.png")

注意：當將 PipelineQuantizationConfig 與 bitsandbytes 結合使用時，您需要分別從 diffusers 匯入 DiffusersBitsAndBytesConfig 並從 transformers 匯入 TransformersBitsAndBytesConfig。這是因為這些元件來源於不同的庫。如果您更喜歡一個更簡單的設定，而無需管理這些不同的匯入，您可以採用另一種方法進行管道級量化，此方法的示例可在 Diffusers 文件的管道級量化部分中找到。

@@
- from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
+ from diffusers import TorchAoConfig as DiffusersTorchAoConfig

- from transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig
+ from transformers import TorchAoConfig as TransformersTorchAoConfig
@@
pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
-         "transformer": DiffusersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
-         "text_encoder_2": TransformersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
+         "transformer": DiffusersTorchAoConfig("int8_weight_only"),
+         "text_encoder_2": TransformersTorchAoConfig("int8_weight_only"),
    }
)

@@
- from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
+ from diffusers import TorchAoConfig as DiffusersTorchAoConfig

- from transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig
+ from transformers import TorchAoConfig as TransformersTorchAoConfig
@@
pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
-         "transformer": DiffusersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
-         "text_encoder_2": TransformersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
+         "transformer": DiffusersTorchAoConfig("int4_weight_only"),
+         "text_encoder_2": TransformersTorchAoConfig("int4_weight_only"),
    }
)

pipe = FluxPipeline.from_pretrained(
    model_id,
    quantization_config=pipeline_quant_config,
    torch_dtype=torch.bfloat16,
+    device_map="balanced"
)
- pipe.to("cuda")

@@
- from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
+ from diffusers import QuantoConfig as DiffusersQuantoConfig

- from transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig
+ from transformers import QuantoConfig as TransformersQuantoConfig
@@
pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
-         "transformer": DiffusersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
-         "text_encoder_2": TransformersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
+         "transformer": DiffusersQuantoConfig(weights_dtype="int8"),
+         "text_encoder_2": TransformersQuantoConfig(weights_dtype="int8"),
    }
)

import torch
from diffusers import AutoModel, FluxPipeline
from transformers import T5EncoderModel
from optimum.quanto import freeze, qfloat8, quantize

model_id = "black-forest-labs/FLUX.1-dev"

text_encoder_2 = T5EncoderModel.from_pretrained(
    model_id,
    subfolder="text_encoder_2",
    torch_dtype=torch.bfloat16,
)

quantize(text_encoder_2, weights=qfloat8)
freeze(text_encoder_2)

transformer = AutoModel.from_pretrained(
      model_id,
      subfolder="transformer",
      torch_dtype=torch.bfloat16,
)

quantize(transformer, weights=qfloat8)
freeze(transformer)

pipe = FluxPipeline.from_pretrained(
    model_id,
    transformer=transformer,
    text_encoder_2=text_encoder_2,
    torch_dtype=torch.bfloat16
).to("cuda")

import torch
from diffusers import FluxPipeline, FluxTransformer2DModel, GGUFQuantizationConfig

model_id = "black-forest-labs/FLUX.1-dev"

# Path to a pre-quantized GGUF file
ckpt_path = "https://huggingface.co/city96/FLUX.1-dev-gguf/resolve/main/flux1-dev-Q4_1.gguf"

transformer = FluxTransformer2DModel.from_single_file(
    ckpt_path,
    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
    torch_dtype=torch.bfloat16,
)

pipe = FluxPipeline.from_pretrained(
    model_id,
    transformer=transformer,
    torch_dtype=torch.bfloat16,
)
pipe.to("cuda")

import torch
from diffusers import FluxPipeline
from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig
from diffusers.quantizers import PipelineQuantizationConfig
from transformers import BitsAndBytesConfig as TransformersBitsAndBytesConfig

model_id = "black-forest-labs/FLUX.1-dev"

pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
        "transformer": DiffusersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
        "text_encoder_2": TransformersBitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16),
    }
)

pipe = FluxPipeline.from_pretrained(
    model_id,
    quantization_config=pipeline_quant_config,
    torch_dtype=torch.bfloat16
)
- pipe.to("cuda")
+ pipe.enable_model_cpu_offload()

import torch
from diffusers import FluxPipeline, AutoModel

model_id = "black-forest-labs/FLUX.1-dev"

transformer = AutoModel.from_pretrained(
    model_id,
    subfolder="transformer",
    torch_dtype=torch.bfloat16,
    # device_map="cuda"
)
transformer.enable_layerwise_casting(storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16)
+ transformer.enable_group_offload(onload_device=torch.device("cuda"), offload_device=torch.device("cpu"), offload_type="leaf_level", use_stream=True)

pipe = FluxPipeline.from_pretrained(model_id, transformer=transformer, torch_dtype=torch.bfloat16)
- pipe.to("cuda")

import torch
from diffusers import FluxPipeline
from diffusers import TorchAoConfig as DiffusersTorchAoConfig
from diffusers.quantizers import PipelineQuantizationConfig
from transformers import TorchAoConfig as TransformersTorchAoConfig

from torchao.quantization import Float8WeightOnlyConfig

model_id = "black-forest-labs/FLUX.1-dev"
dtype = torch.bfloat16

pipeline_quant_config = PipelineQuantizationConfig(
    quant_mapping={
        "transformer":DiffusersTorchAoConfig("int4_weight_only"),
        "text_encoder_2": TransformersTorchAoConfig("int4_weight_only"),
    }
)

pipe = FluxPipeline.from_pretrained(
    model_id,
    quantization_config=pipeline_quant_config,
    torch_dtype=torch.bfloat16,
    device_map="balanced"
)

+ pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)

注意： torch.compile 可能會引入細微的數值差異，導致影像輸出發生變化。