استكشاف الواجهات الخلفية للتكميم في الناشرين

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")

ملحوظة: عند الاستخدام PipelineQuantizationConfig مع bitsandbytes، تحتاج إلى الاستيراد DiffusersBitsAndBytesConfig من diffusers و TransformersBitsAndBytesConfig من transformers بشكل منفصل. وذلك لأن هذه المكونات تنشأ من مكتبات مختلفة. إذا كنت تفضل إعدادًا أبسط دون إدارة هذه الواردات المميزة، فيمكنك استخدام أسلوب بديل للتكميم على مستوى خط الأنابيب، ويوجد مثال على هذه الطريقة في وثائق Diffusers حول التكميم على مستوى خط الأنابيب.

@@
- 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"


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)

ملحوظة: torch.compile يمكن أن يقدم اختلافات رقمية دقيقة، مما يؤدي إلى تغييرات في إخراج الصورة