• Stars
    star
    127
  • Rank 273,911 (Top 6 %)
  • Language
    Python
  • License
    Apache License 2.0
  • Created 6 months ago
  • Updated 3 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Faster generation with text-to-image diffusion models.

Diffusion, fast

Repository for the blog post: Accelerating Generative AI Part III: Diffusion, Fast. You can find a run down of the techniques on the ๐Ÿค— Diffusers website too.


Summary of the optimizations:

  • Running with the bfloat16 precision
  • scaled_dot_product_attention (SPDA)
  • torch.compile
  • Combining q,k,v projections for attention computation
  • Dynamic int8 quantization

These techniques are fairly generalizable to other pipelines too, as we show below.

Table of contents:

Setup ๐Ÿ› ๏ธ

We rely on pure PyTorch for the optimizations. You can refer to the Dockerfile to get the complete development environment setup.

For hardware, we used an 80GB 400W A100 GPU with its memory clock set to the maximum rate (1593 in our case).

Running a benchmarking experiment ๐ŸŽ๏ธ

run_benchmark.py is the main script for benchmarking the different optimization techniques. After an experiment has been done, you should expect to see two files:

  • A .csv file with all the benchmarking numbers.
  • A .jpeg image file corresponding to the experiment.

Refer to the experiment-scripts/run_sd.sh for some reference experiment commands.

Notes on running PixArt-Alpha experiments:

  • Use the run_experiment_pixart.py for this.
  • Uninstall the current installation of diffusers and re-install it again like so: pip install git+https://github.com/huggingface/diffusers@fuse-projections-pixart.
  • Refer to the experiment-scripts/run_pixart.sh script for some reference experiment commands.

(Support for PixArt-Alpha is experimental.)

You can use the prepare_results.py script to generate a consolidated CSV file and a plot to visualize the results from it. This is best used after you have run a couple of benchmarking experiments already and have their corresponding CSV files.

To run the script, you need the following dependencies:

  • pandas
  • matplotlib
  • seaborn

Improvements, progressively ๐Ÿ“ˆ ๐Ÿ“Š

Baseline
from diffusers import StableDiffusionXLPipeline

# Load the pipeline in full-precision and place its model components on CUDA.
pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0"
).to("cuda")

# Run the attention ops without efficiency.
pipe.unet.set_default_attn_processor()
pipe.vae.set_default_attn_processor()

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt, num_inference_steps=30).images[0]

With this, we're at:

Bfloat16
from diffusers import StableDiffusionXLPipeline
import torch

pipe = StableDiffusionXLPipeline.from_pretrained(
	"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.bfloat16
).to("cuda")

# Run the attention ops without efficiency.
pipe.unet.set_default_attn_processor()
pipe.vae.set_default_attn_processor()

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt, num_inference_steps=30).images[0]

๐Ÿ’ก We later ran the experiments in float16 and found out that the recent versions of torchao do not incur numerical problems from float16.

scaled_dot_product_attention
from diffusers import StableDiffusionXLPipeline
import torch

pipe = StableDiffusionXLPipeline.from_pretrained(
	"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.bfloat16
).to("cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt, num_inference_steps=30).images[0]
torch.compile

First, configure some compiler flags:

from diffusers import StableDiffusionXLPipeline
import torch

# Set the following compiler flags to make things go brrr.
torch._inductor.config.conv_1x1_as_mm = True
torch._inductor.config.coordinate_descent_tuning = True
torch._inductor.config.epilogue_fusion = False
torch._inductor.config.coordinate_descent_check_all_directions = True

Then load the pipeline:

pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.bfloat16
).to("cuda")

Compile and perform inference:

# Compile the UNet and VAE.
pipe.unet.to(memory_format=torch.channels_last)
pipe.vae.to(memory_format=torch.channels_last)
pipe.unet = torch.compile(pipe.unet, mode="max-autotune", fullgraph=True)
pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# First call to `pipe` will be slow, subsequent ones will be faster.
image = pipe(prompt, num_inference_steps=30).images[0]
Combining attention projection matrices
from diffusers import StableDiffusionXLPipeline
import torch

# Configure the compiler flags.
torch._inductor.config.conv_1x1_as_mm = True
torch._inductor.config.coordinate_descent_tuning = True
torch._inductor.config.epilogue_fusion = False
torch._inductor.config.coordinate_descent_check_all_directions = True

pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.bfloat16
).to("cuda")

# Combine attention projection matrices.
pipe.fuse_qkv_projections()

# Compile the UNet and VAE.
pipe.unet.to(memory_format=torch.channels_last)
pipe.vae.to(memory_format=torch.channels_last)
pipe.unet = torch.compile(pipe.unet, mode="max-autotune", fullgraph=True)
pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# First call to `pipe` will be slow, subsequent ones will be faster.
image = pipe(prompt, num_inference_steps=30).images[0]
Dynamic quantization

Start by setting the compiler flags (this time, we have two new):

from diffusers import StableDiffusionXLPipeline
import torch

from torchao.quantization import apply_dynamic_quant, swap_conv2d_1x1_to_linear

# Compiler flags. There are two new.
torch._inductor.config.conv_1x1_as_mm = True
torch._inductor.config.coordinate_descent_tuning = True
torch._inductor.config.epilogue_fusion = False
torch._inductor.config.coordinate_descent_check_all_directions = True
torch._inductor.config.force_fuse_int_mm_with_mul = True
torch._inductor.config.use_mixed_mm = True

Then write the filtering functions to apply dynamic quantization:

def dynamic_quant_filter_fn(mod, *args):
    return (
        isinstance(mod, torch.nn.Linear)
        and mod.in_features > 16
        and (mod.in_features, mod.out_features)
        not in [
            (1280, 640),
            (1920, 1280),
            (1920, 640),
            (2048, 1280),
            (2048, 2560),
            (2560, 1280),
            (256, 128),
            (2816, 1280),
            (320, 640),
            (512, 1536),
            (512, 256),
            (512, 512),
            (640, 1280),
            (640, 1920),
            (640, 320),
            (640, 5120),
            (640, 640),
            (960, 320),
            (960, 640),
        ]
    )


def conv_filter_fn(mod, *args):
    return (
        isinstance(mod, torch.nn.Conv2d) and mod.kernel_size == (1, 1) and 128 in [mod.in_channels, mod.out_channels]
    )

Then we're rwady for inference:

pipe = StableDiffusionXLPipeline.from_pretrained(
	"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.bfloat16
).to("cuda")

# Combine attention projection matrices.
pipe.fuse_qkv_projections()

# Change the memory layout.
pipe.unet.to(memory_format=torch.channels_last)
pipe.vae.to(memory_format=torch.channels_last)

# Swap the pointwise convs with linears.
swap_conv2d_1x1_to_linear(pipe.unet, conv_filter_fn)
swap_conv2d_1x1_to_linear(pipe.vae, conv_filter_fn)

# Apply dynamic quantization.
apply_dynamic_quant(pipe.unet, dynamic_quant_filter_fn)
apply_dynamic_quant(pipe.vae, dynamic_quant_filter_fn)

# Compile.
pipe.unet = torch.compile(pipe.unet, mode="max-autotune", fullgraph=True)
pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt, num_inference_steps=30).images[0]

Results from other pipelines ๐ŸŒ‹

SSD-1B
SD v1-5
Pixart-Alpha

More Repositories

1

transformers

๐Ÿค— Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python
125,891
star
2

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Python
28,073
star
3

diffusers

๐Ÿค— Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Python
22,776
star
4

datasets

๐Ÿค— The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Python
17,530
star
5

peft

๐Ÿค— PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python
14,007
star
6

candle

Minimalist ML framework for Rust
Rust
12,686
star
7

tokenizers

๐Ÿ’ฅ Fast State-of-the-Art Tokenizers optimized for Research and Production
Rust
8,286
star
8

trl

Train transformer language models with reinforcement learning.
Python
8,181
star
9

text-generation-inference

Large Language Model Text Generation Inference
Python
7,240
star
10

accelerate

๐Ÿš€ A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Python
7,008
star
11

chat-ui

Open source codebase powering the HuggingChat app
TypeScript
6,369
star
12

deep-rl-class

This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.
MDX
3,541
star
13

alignment-handbook

Robust recipes to align language models with human and AI preferences
Python
3,485
star
14

autotrain-advanced

๐Ÿค— AutoTrain Advanced
Python
3,283
star
15

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course
Jupyter Notebook
3,126
star
16

notebooks

Notebooks using the Hugging Face libraries ๐Ÿค—
Jupyter Notebook
3,114
star
17

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Python
2,964
star
18

neuralcoref

โœจFast Coreference Resolution in spaCy with Neural Networks
C
2,806
star
19

knockknock

๐ŸšชโœŠKnock Knock: Get notified when your training ends with only two additional lines of code
Python
2,682
star
20

swift-coreml-diffusers

Swift app demonstrating Core ML Stable Diffusion
Swift
2,377
star
21

safetensors

Simple, safe way to store and distribute tensors
Python
2,347
star
22

optimum

๐Ÿš€ Accelerate training and inference of ๐Ÿค— Transformers and ๐Ÿค— Diffusers with easy to use hardware optimization tools
Python
2,086
star
23

awesome-papers

Papers & presentation materials from Hugging Face's internal science day
1,996
star
24

blog

Public repo for HF blog posts
Jupyter Notebook
1,962
star
25

setfit

Efficient few-shot learning with Sentence Transformers
Jupyter Notebook
1,912
star
26

text-embeddings-inference

A blazing fast inference solution for text embeddings models
Rust
1,845
star
27

course

The Hugging Face course on Transformers
MDX
1,832
star
28

evaluate

๐Ÿค— Evaluate: A library for easily evaluating machine learning models and datasets.
Python
1,825
star
29

transfer-learning-conv-ai

๐Ÿฆ„ State-of-the-Art Conversational AI with Transfer Learning
Python
1,654
star
30

swift-coreml-transformers

Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!
Swift
1,543
star
31

pytorch-openai-transformer-lm

๐ŸฅA PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Python
1,464
star
32

cookbook

Open-source AI cookbook
Jupyter Notebook
1,357
star
33

huggingface_hub

All the open source things related to the Hugging Face Hub.
Python
1,311
star
34

Mongoku

๐Ÿ”ฅThe Web-scale GUI for MongoDB
TypeScript
1,289
star
35

huggingface.js

Utilities to use the Hugging Face Hub API
TypeScript
1,193
star
36

hmtl

๐ŸŒŠHMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP
Python
1,185
star
37

gsplat.js

JavaScript Gaussian Splatting library.
TypeScript
1,114
star
38

llm-vscode

LLM powered development for VSCode
TypeScript
1,060
star
39

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Python
1,033
star
40

pytorch-pretrained-BigGAN

๐Ÿฆ‹A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
Python
986
star
41

torchMoji

๐Ÿ˜‡A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc
Python
880
star
42

nanotron

Minimalistic large language model 3D-parallelism training
Python
810
star
43

naacl_transfer_learning_tutorial

Repository of code for the tutorial on Transfer Learning in NLP held at NAACL 2019 in Minneapolis, MN, USA
Python
718
star
44

awesome-huggingface

๐Ÿค— A list of wonderful open-source projects & applications integrated with Hugging Face libraries.
698
star
45

optimum-nvidia

Python
680
star
46

dataset-viewer

Lightweight web API for visualizing and exploring any dataset - computer vision, speech, text, and tabular - stored on the Hugging Face Hub
Python
614
star
47

transformers-bloom-inference

Fast Inference Solutions for BLOOM
Python
546
star
48

exporters

Export Hugging Face models to Core ML and TensorFlow Lite
Python
540
star
49

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch
C++
523
star
50

llm.nvim

LLM powered development for Neovim
Lua
507
star
51

swift-transformers

Swift Package to implement a transformers-like API in Swift
Swift
482
star
52

node-question-answering

Fast and production-ready question answering in Node.js
TypeScript
459
star
53

large_language_model_training_playbook

An open collection of implementation tips, tricks and resources for training large language models
Python
431
star
54

llm-ls

LSP server leveraging LLMs for code completion (and more?)
Rust
416
star
55

llm_training_handbook

An open collection of methodologies to help with successful training of large language models.
Python
385
star
56

swift-chat

Mac app to demonstrate swift-transformers
Swift
375
star
57

tflite-android-transformers

DistilBERT / GPT-2 for on-device inference thanks to TensorFlow Lite with Android demo apps
Java
368
star
58

community-events

Place where folks can contribute to ๐Ÿค— community events
Jupyter Notebook
368
star
59

nn_pruning

Prune a model while finetuning or training.
Jupyter Notebook
360
star
60

text-clustering

Easily embed, cluster and semantically label text datasets
Python
335
star
61

speechbox

Python
328
star
62

100-times-faster-nlp

๐Ÿš€100 Times Faster Natural Language Processing in Python - iPython notebook
HTML
325
star
63

education-toolkit

Educational materials for universities
Jupyter Notebook
307
star
64

controlnet_aux

Python
306
star
65

optimum-intel

๐Ÿค— Optimum Intel: Accelerate inference with Intel optimization tools
Jupyter Notebook
295
star
66

datablations

Scaling Data-Constrained Language Models
Jupyter Notebook
293
star
67

unity-api

C#
284
star
68

open-muse

Open reproduction of MUSE for fast text2image generation.
Python
284
star
69

audio-transformers-course

The Hugging Face Course on Transformers for Audio
MDX
247
star
70

hub-docs

Docs of the Hugging Face Hub
221
star
71

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.
Python
208
star
72

quanto

A pytorch Quantization Toolkit
Python
201
star
73

simulate

๐ŸŽข Creating and sharing simulation environments for embodied and synthetic data research
Python
185
star
74

ratchet

A cross-platform browser ML framework.
Rust
184
star
75

optimum-benchmark

A unified multi-backend utility for benchmarking Transformers, Timm, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
Python
183
star
76

hf_transfer

Rust
181
star
77

olm-datasets

Pipeline for pulling and processing online language model pretraining data from the web
Python
169
star
78

instruction-tuned-sd

Code for instruction-tuning Stable Diffusion.
Python
167
star
79

optimum-neuron

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.
Jupyter Notebook
163
star
80

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters
Python
156
star
81

OBELICS

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.
Python
147
star
82

workshops

Materials for workshops on the Hugging Face ecosystem
Jupyter Notebook
146
star
83

cosmopedia

Python
138
star
84

api-inference-community

Python
131
star
85

diarizers

Python
106
star
86

optimum-habana

Easy and lightning fast training of ๐Ÿค— Transformers on Habana Gaudi processor (HPU)
Python
106
star
87

sharp-transformers

A Unity plugin for using Transformers models in Unity.
C#
104
star
88

competitions

Python
101
star
89

hf-hub

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package
Rust
93
star
90

olm-training

Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.
Python
87
star
91

fuego

[WIP] A ๐Ÿ”ฅ interface for running code in the cloud
Python
84
star
92

tune

Python
83
star
93

datasets-viewer

Viewer for the ๐Ÿค— datasets library.
Python
82
star
94

optimum-graphcore

Blazing fast training of ๐Ÿค— Transformers on Graphcore IPUs
Python
78
star
95

frp

FRP Fork
Go
73
star
96

paper-style-guide

72
star
97

block_movement_pruning

Block Sparse movement pruning
Python
70
star
98

amused

Python
68
star
99

doc-builder

The package used to build the documentation of our Hugging Face repos
Python
67
star
100

data-measurements-tool

Developing tools to automatically analyze datasets
Python
67
star