NOTE: stable-fast
is only in beta stage and is prone to be buggy, feel free to try it out and give suggestions!
stable-fast
is an ultra lightweight inference optimization library for HuggingFace Diffusers on NVIDIA GPUs.
stable-fast
provides super fast inference optimization by utilizing some key techniques and features:
- CUDNN Convolution Fusion:
stable-fast
implements a series of fully-functional and fully-compatible CUDNN convolution fusion operators for all kinds of combinations ofConv + Bias + Add + Act
computation patterns. - Low Precision & Fused GEMM:
stable-fast
implements a series of fused GEMM operators that compute withfp16
precision, which is fast than PyTorch's defaults (read & write withfp16
while compute withfp32
). - NHWC & Fused GroupNorm:
stable-fast
implements a highly optimized fused NHWCGroupNorm + GELU
operator with OpenAI'striton
, which eliminates the need of memory format permutation operators. - Fully Traced Model:
stable-fast
improves thetorch.jit.trace
interface to make it more proper for tracing complex models. Nearly every part ofStableDiffusionPipeline
can be traced and converted to TorchScript. It is more stable thantorch.compile
and has a significantly lower CPU overhead thantorch.compile
and supports ControlNet and LoRA. - CUDA Graph:
stable-fast
can capture the UNet structure into CUDA Graph format, which can reduce the CPU overhead when the batch size is small. - Fused Multihead Attention:
stable-fast
just uses xformers and make it compatible with TorchScript.
- Fast:
stable-fast
is specialy optimized for HuggingFace Diffusers. It achieves the best performance over all libraries. - Minimal:
stable-fast
works as a plugin framework forPyTorch
. it utilizes existingPyTorch
functionality and infrastructures and is compatible with other acceleration techniques, as well as popular fine-tuning techniques and deployment solutions.
Framework | Performance |
---|---|
Vanilla PyTorch | 23 it/s |
AITemplate | 44 it/s |
TensorRT | 52 it/s |
OneFlow | 55 it/s |
Stable Fast (with xformers & triton) | 60 it/s |
Framework | Performance |
---|---|
Vanilla PyTorch | 16 it/s |
AITemplate | 31 it/s |
TensorRT | 33 it/s |
OneFlow | 39 it/s |
Stable Fast (with xformers & triton) | 38 it/s |
NOTE: stable-fast
is currently only tested on Linux. You need to install PyTorch with CUDA support at first (versions from 1.12 to 2.1 are suggested).
# Make sure you have CUDNN/CUBLAS installed.
# https://developer.nvidia.com/cudnn
# https://developer.nvidia.com/cublas
# Install PyTorch with CUDA and other packages at first
pip install torch diffusers xformers 'triton>=2.1.0'
# (Optional) Makes the build much faster
pip install ninja
# Set TORCH_CUDA_ARCH_LIST if running and building on different GPU types
pip install -v -U git+https://github.com/chengzeyi/stable-fast.git@main#egg=stable-fast
# (this can take dozens of minutes)
NOTE: Any usage outside sfast.compilers
is not guaranteed to be backward compatible.
NOTE: To get the best performance, xformers
and OpenAI's triton>=2.1.0
need to be installed and enabled. You might need to build xformers
from source to make it compatible with your PyTorch
.
# TCMalloc is highly suggested to reduce CPU overhead
# https://github.com/google/tcmalloc
LD_PRELOAD=/path/to/libtcmalloc.so python3 ...
import packaging.version
import torch
if packaging.version.parse(torch.__version__) >= packaging.version.parse('1.12.0'):
torch.backends.cuda.matmul.allow_tf32 = True
import torch
from diffusers import StableDiffusionPipeline
from sfast.compilers.stable_diffusion_pipeline_compiler import (compile,
CompilationConfig
)
def load_model():
model = StableDiffusionPipeline.from_pretrained(
'runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16)
model.safety_checker = None
model.to(torch.device('cuda'))
return model
model = load_model()
config = CompilationConfig.Default()
# xformers and triton are suggested for achieving best performance.
# It might be slow for triton to generate, compile and fine-tune kernels.
try:
import xformers
config.enable_xformers = True
except ImportError:
print('xformers not installed, skip')
try:
import triton
config.enable_triton = True
except ImportError:
print('triton not installed, skip')
# CUDA Graph is suggested for small batch sizes.
# After capturing, the model only accepts one fixed image size.
# If you want the model to be dynamic, don't enable it.
config.enable_cuda_graph = True
compiled_model = compile(model, config)
kwarg_inputs = dict(
prompt=
'(masterpiece:1,2), best quality, masterpiece, best detail face, lineart, monochrome, a beautiful girl',
height=512,
width=512,
num_inference_steps=50,
num_images_per_prompt=1,
)
# NOTE: Warm it up.
# The first call will trigger compilation and might be very slow.
# After the first call, it should be very fast.
output_image = compiled_model(**kwarg_inputs).images[0]
# Let's see the second call!
output_image = compiled_model(**kwarg_inputs).images[0]