ParaAttention

要在 FLUX.1-dev 上应用第一块缓存，请按照下方所示调用 apply_cache_on_pipe。0.08 是 FLUX 模型的默认残差差异值。

import time
import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    dtype=torch.bfloat16,
).to("cuda")  # or "mps", "xpu", "cpu"

from para_attn.first_block_cache.diffusers_adapters import apply_cache_on_pipe

apply_cache_on_pipe(pipe, residual_diff_threshold=0.08)

# Enable memory savings
# pipe.enable_model_cpu_offload()
# pipe.enable_sequential_cpu_offload()

begin = time.time()
image = pipe(
    "A cat holding a sign that says hello world",
    num_inference_steps=28,
).images[0]
end = time.time()
print(f"Time: {end - begin:.2f}s")

print("Saving image to flux.png")
image.save("flux.png")

优化	原始	FBCache rdt=0.06	FBCache rdt=0.08	FBCache rdt=0.10	FBCache rdt=0.12
预览
实际耗时（秒）	26.36	21.83	17.01	16.00	13.78

First Block Cache 将推理速度从基线降低至 17.01 秒，即速度提升了 1.55 倍，同时几乎未造成质量损失。

import time
import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    dtype=torch.bfloat16,
).to("cuda")  # or "mps", "xpu", "cpu"

from para_attn.first_block_cache.diffusers_adapters import apply_cache_on_pipe

apply_cache_on_pipe(
    pipe,
    residual_diff_threshold=0.12,  # Use a larger value to make the cache take effect
)

from torchao.quantization import quantize_, float8_dynamic_activation_float8_weight, float8_weight_only

quantize_(pipe.text_encoder, float8_weight_only())
quantize_(pipe.transformer, float8_dynamic_activation_float8_weight())
pipe.transformer = torch.compile(
   pipe.transformer, mode="max-autotune-no-cudagraphs",
)

# Enable memory savings
# pipe.enable_model_cpu_offload()
# pipe.enable_sequential_cpu_offload()

for i in range(2):
    begin = time.time()
    image = pipe(
        "A cat holding a sign that says hello world",
        num_inference_steps=28,
    ).images[0]
    end = time.time()
    if i == 0:
        print(f"Warm up time: {end - begin:.2f}s")
    else:
        print(f"Time: {end - begin:.2f}s")

print("Saving image to flux.png")
image.save("flux.png")

fp8 动态量化和 torch.compile 将推理速度降低至 7.56 秒，相较于基线快 3.48 倍。

import time
import torch
from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
from diffusers.utils import export_to_video

model_id = "tencent/HunyuanVideo"
transformer = HunyuanVideoTransformer3DModel.from_pretrained(
    model_id,
    subfolder="transformer",
    dtype=torch.bfloat16,
    revision="refs/pr/18",
)
pipe = HunyuanVideoPipeline.from_pretrained(
    model_id,
    transformer=transformer,
    dtype=torch.float16,
    revision="refs/pr/18",
).to("cuda")  # or "mps", "xpu", "cpu"

from para_attn.first_block_cache.diffusers_adapters import apply_cache_on_pipe

apply_cache_on_pipe(pipe)

from torchao.quantization import quantize_, float8_dynamic_activation_float8_weight, float8_weight_only

quantize_(pipe.text_encoder, float8_weight_only())
quantize_(pipe.transformer, float8_dynamic_activation_float8_weight())
pipe.transformer = torch.compile(
   pipe.transformer, mode="max-autotune-no-cudagraphs",
)

# Enable memory savings
pipe.vae.enable_tiling()
# pipe.enable_model_cpu_offload()
# pipe.enable_sequential_cpu_offload()

for i in range(2):
    begin = time.time()
    output = pipe(
        prompt="A cat walks on the grass, realistic",
        height=720,
        width=1280,
        num_frames=129,
        num_inference_steps=1 if i == 0 else 30,
    ).frames[0]
    end = time.time()
    if i == 0:
        print(f"Warm up time: {end - begin:.2f}s")
    else:
        print(f"Time: {end - begin:.2f}s")

print("Saving video to hunyuan_video.mp4")
export_to_video(output, "hunyuan_video.mp4", fps=15)

NVIDIA L20 GPU 仅有 48GB 显存，在编译后，如果未调用 enable_model_cpu_offload，可能会遇到内存溢出（OOM）错误，因为 HunyuanVideo 在高分辨率和大量帧数下运行时会产生非常大的激活张量。对于显存小于 80GB 的 GPU，可以尝试降低分辨率和帧数以避免 OOM 错误。

大型视频生成模型通常受限于注意力计算，而非全连接层。这些模型从量化和 torch.compile 中获得的收益并不显著。

下面的代码示例结合了 First Block Cache、fp8 动态量化、torch.compile 和 Context Parallelism，以实现最快的推理速度。

import time
import torch
import torch.distributed as dist
from diffusers import FluxPipeline

dist.init_process_group()

torch.cuda.set_device(dist.get_rank())

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    dtype=torch.bfloat16,
).to("cuda")  # or "mps", "xpu", "cpu"

from para_attn.context_parallel import init_context_parallel_mesh
from para_attn.context_parallel.diffusers_adapters import parallelize_pipe
from para_attn.parallel_vae.diffusers_adapters import parallelize_vae

mesh = init_context_parallel_mesh(
    pipe.device.type,
    max_ring_dim_size=2,
)
parallelize_pipe(
    pipe,
    mesh=mesh,
)
parallelize_vae(pipe.vae, mesh=mesh._flatten())

from para_attn.first_block_cache.diffusers_adapters import apply_cache_on_pipe

apply_cache_on_pipe(
    pipe,
    residual_diff_threshold=0.12,  # Use a larger value to make the cache take effect
)

from torchao.quantization import quantize_, float8_dynamic_activation_float8_weight, float8_weight_only

quantize_(pipe.text_encoder, float8_weight_only())
quantize_(pipe.transformer, float8_dynamic_activation_float8_weight())
torch._inductor.config.reorder_for_compute_comm_overlap = True
pipe.transformer = torch.compile(
   pipe.transformer, mode="max-autotune-no-cudagraphs",
)

# Enable memory savings
# pipe.enable_model_cpu_offload(gpu_id=dist.get_rank())
# pipe.enable_sequential_cpu_offload(gpu_id=dist.get_rank())

for i in range(2):
    begin = time.time()
    image = pipe(
        "A cat holding a sign that says hello world",
        num_inference_steps=28,
        output_type="pil" if dist.get_rank() == 0 else "pt",
    ).images[0]
    end = time.time()
    if dist.get_rank() == 0:
        if i == 0:
            print(f"Warm up time: {end - begin:.2f}s")
        else:
            print(f"Time: {end - begin:.2f}s")

if dist.get_rank() == 0:
    print("Saving image to flux.png")
    image.save("flux.png")

dist.destroy_process_group()

将其保存为 run_flux.py，并使用 torchrun 启动。

# Use --nproc_per_node to specify the number of GPUs
torchrun --nproc_per_node=2 run_flux.py

与基线相比，使用 2 块 NVIDIA L20 GPU 时，推理速度降至 8.20 秒，即快 3.21 倍。使用 4 块 L20 时，推理速度为 3.90 秒，即快 6.75 倍。

下面的代码示例结合了 First Block Cache 和 Context Parallelism，以实现最快的推理速度。

import time
import torch
import torch.distributed as dist
from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel
from diffusers.utils import export_to_video

dist.init_process_group()

torch.cuda.set_device(dist.get_rank())

model_id = "tencent/HunyuanVideo"
transformer = HunyuanVideoTransformer3DModel.from_pretrained(
    model_id,
    subfolder="transformer",
    dtype=torch.bfloat16,
    revision="refs/pr/18",
)
pipe = HunyuanVideoPipeline.from_pretrained(
    model_id,
    transformer=transformer,
    dtype=torch.float16,
    revision="refs/pr/18",
).to("cuda")  # or "mps", "xpu", "cpu"

from para_attn.context_parallel import init_context_parallel_mesh
from para_attn.context_parallel.diffusers_adapters import parallelize_pipe
from para_attn.parallel_vae.diffusers_adapters import parallelize_vae

mesh = init_context_parallel_mesh(
    pipe.device.type,
)
parallelize_pipe(
    pipe,
    mesh=mesh,
)
parallelize_vae(pipe.vae, mesh=mesh._flatten())

from para_attn.first_block_cache.diffusers_adapters import apply_cache_on_pipe

apply_cache_on_pipe(pipe)

# from torchao.quantization import quantize_, float8_dynamic_activation_float8_weight, float8_weight_only
#
# torch._inductor.config.reorder_for_compute_comm_overlap = True
#
# quantize_(pipe.text_encoder, float8_weight_only())
# quantize_(pipe.transformer, float8_dynamic_activation_float8_weight())
# pipe.transformer = torch.compile(
#    pipe.transformer, mode="max-autotune-no-cudagraphs",
# )

# Enable memory savings
pipe.vae.enable_tiling()
# pipe.enable_model_cpu_offload(gpu_id=dist.get_rank())
# pipe.enable_sequential_cpu_offload(gpu_id=dist.get_rank())

for i in range(2):
    begin = time.time()
    output = pipe(
        prompt="A cat walks on the grass, realistic",
        height=720,
        width=1280,
        num_frames=129,
        num_inference_steps=1 if i == 0 else 30,
        output_type="pil" if dist.get_rank() == 0 else "pt",
    ).frames[0]
    end = time.time()
    if dist.get_rank() == 0:
        if i == 0:
            print(f"Warm up time: {end - begin:.2f}s")
        else:
            print(f"Time: {end - begin:.2f}s")

if dist.get_rank() == 0:
    print("Saving video to hunyuan_video.mp4")
    export_to_video(output, "hunyuan_video.mp4", fps=15)

dist.destroy_process_group()

将其保存为 run_hunyuan_video.py，并使用 torchrun 启动。

# Use --nproc_per_node to specify the number of GPUs
torchrun --nproc_per_node=8 run_hunyuan_video.py

与基线相比，使用 8 块 NVIDIA L20 GPU 时，推理速度降低至 649.23 秒，即快了 5.66 倍。

GPU 类型	GPU 数量	优化	实际耗时（秒）	加速
NVIDIA L20	1	基线	26.36	1.00x
NVIDIA L20	1	FBCache (rdt=0.08)	17.01	1.55x
NVIDIA L20	1	FP8 DQ	13.40	1.96x
NVIDIA L20	1	FBCache (rdt=0.12) + FP8 DQ	7.56	3.48x
NVIDIA L20	2	FBCache (rdt=0.12) + FP8 DQ + CP	4.92	5.35x
NVIDIA L20	4	FBCache (rdt=0.12) + FP8 DQ + CP	3.90	6.75x

GPU 类型	GPU 数量	优化	实际耗时（秒）	加速
NVIDIA L20	1	基线	3675.71	1.00x
NVIDIA L20	1	FBCache	2271.06	1.62x
NVIDIA L20	2	FBCache + CP	1132.90	3.24x
NVIDIA L20	4	FBCache + CP	718.15	5.12x
NVIDIA L20	8	FBCache + CP	649.23	5.66x

Diffusers

第一块缓存

fp8 量化

上下文并行

基准测试