Skip to content

Commit 4d5fe8c

Browse files
aimen-djariaimen-djari
committed
fix format
1 parent 0beee8d commit 4d5fe8c

File tree

2 files changed

+76
-43
lines changed

2 files changed

+76
-43
lines changed

‎.vitepress/sidebar.ts‎

Lines changed: 0 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,6 @@ export function getSidebar() {
5050
text: 'Develop with AI',
5151
link: '/get-started/develop-with-ai',
5252
},
53-
5453
],
5554
},
5655
{
@@ -103,8 +102,6 @@ export function getSidebar() {
103102
},
104103
],
105104
},
106-
107-
108105
],
109106
'/guides/': [
110107
{

‎src/protocol/ai.md‎

Lines changed: 76 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -1,36 +1,55 @@
11
---
22
title: iExec for AI
3-
description: How iExec helps develop, deploy and execute confidential AI applications with framework support
3+
description:
4+
How iExec helps develop, deploy and execute confidential AI applications with
5+
framework support
46
---
57

68
# 🧠 iExec for AI
79

8-
The iExec Platform delivers powerful tools specifically for AI developers. Build, deploy, and execute confidential AI applications with enterprise-grade security and decentralized infrastructure.
10+
The iExec Platform delivers powerful tools specifically for AI developers.
11+
Build, deploy, and execute confidential AI applications with enterprise-grade
12+
security and decentralized infrastructure.
913

1014
## 🚀 Quick Start
1115

1216
**Want to get started immediately?**
13-
- 📚 **[AI Frameworks Hello World](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world)** - Ready-to-use Docker examples for TensorFlow, PyTorch, and more
14-
- 🛠️ **[Build & Deploy](/guides/build-iapp/build-&-deploy)** - General iApp development guide (not AI-specific)
15-
- 🔬 **[TDX App Guide](/guides/build-iapp/advanced/create-your-first-tdx-app)** - Build TDX applications (works well for AI workloads)
17+
18+
- 📚
19+
**[AI Frameworks Hello World](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world)** -
20+
Ready-to-use Docker examples for TensorFlow, PyTorch, and more
21+
- 🛠️ **[Build & Deploy](/guides/build-iapp/build-&-deploy)** - General iApp
22+
development guide (not AI-specific)
23+
- 🔬
24+
**[TDX App Guide](/guides/build-iapp/advanced/create-your-first-tdx-app)** -
25+
Build TDX applications (works well for AI workloads)
1626

1727
## 🛡️ Why iExec for AI?
1828

1929
### Confidential Computing
20-
Your AI models and data are protected end-to-end using Trusted Execution Environments (TEEs):
30+
31+
Your AI models and data are protected end-to-end using Trusted Execution
32+
Environments (TEEs):
33+
2134
- **Data Privacy**: AI computations are encrypted throughout processing
22-
- **Secure Training & Inference**: Models and data can never be accessed by unauthorized entities
23-
- **Hardware-Level Security**: Intel SGX and TDX provide military-grade protection
35+
- **Secure Training & Inference**: Models and data can never be accessed by
36+
unauthorized entities
37+
- **Hardware-Level Security**: Intel SGX and TDX provide military-grade
38+
protection
2439

2540
### AI Monetization
41+
2642
Monetize your AI assets easily and securely:
43+
2744
- **Datasets**: Encrypt and sell access to your training data
2845
- **Models**: Deploy and monetize your trained AI models
2946
- **Agents**: Create and sell AI agents and applications
3047
- **Ownership Preserved**: Your digital assets always remain yours
3148

3249
### Decentralized Infrastructure
50+
3351
Scale AI applications without centralized cloud dependencies:
52+
3453
- **On-Demand Compute**: Access powerful resources when you need them
3554
- **Fair Pricing**: Transparent, blockchain-verified execution costs
3655
- **Global Network**: Deploy across a worldwide network of secure workers
@@ -39,30 +58,33 @@ Scale AI applications without centralized cloud dependencies:
3958

4059
### Overview
4160

42-
| Framework | TDX Support | SGX Support | Best For |
43-
|-----------|-------------|-------------|----------|
44-
| **TensorFlow** | ✅ Yes (3.01GB) | ❌ No | Deep learning, production ML |
45-
| **PyTorch** | ✅ Yes (6.44GB) | ❌ No | Research, computer vision |
61+
| Framework | TDX Support | SGX Support | Best For |
62+
| ---------------- | --------------- | --------------- | ----------------------------- |
63+
| **TensorFlow** | ✅ Yes (3.01GB) | ❌ No | Deep learning, production ML |
64+
| **PyTorch** | ✅ Yes (6.44GB) | ❌ No | Research, computer vision |
4665
| **Scikit-learn** | ✅ Yes (1.18GB) | ✅ Yes (1.01GB) | Traditional ML, data analysis |
47-
| **OpenVINO** | ✅ Yes (1.82GB) | ❌ No | Computer vision, inference |
48-
| **NumPy** | ✅ Yes (1.25GB) | ✅ Yes (1.08GB) | Scientific computing |
49-
| **Matplotlib** | ✅ Yes (1.25GB) | ✅ Yes (1.08GB) | Data visualization |
66+
| **OpenVINO** | ✅ Yes (1.82GB) | ❌ No | Computer vision, inference |
67+
| **NumPy** | ✅ Yes (1.25GB) | ✅ Yes (1.08GB) | Scientific computing |
68+
| **Matplotlib** | ✅ Yes (1.25GB) | ✅ Yes (1.08GB) | Data visualization |
5069

5170
### Framework Details
5271

53-
| Framework | Version | Description | TDX Support | SGX Support | Use Cases | Resources |
54-
|-----------|---------|-------------|-------------|-------------|-----------|-----------|
55-
| **TensorFlow** | 2.19.0 | Google's ML framework for production AI | ✅ 3.01GB | ❌ Too large | Deep learning, CV, NLP | [Docs](https://www.tensorflow.org/) • [Quickstart](https://www.tensorflow.org/tutorials/quickstart/beginner) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/tensorflow) |
56-
| **PyTorch** | 2.7.0+cu126 | Facebook's research-focused DL framework | ✅ 6.44GB | ❌ Too large | Research, DL, CV, NLP | [Docs](https://pytorch.org/docs/) • [Quickstart](https://docs.pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/pytorch) |
57-
| **Scikit-learn** | 1.6.1 | Comprehensive ML library for Python | ✅ 1.18GB | ✅ 1.01GB | Classification, regression, clustering | [Docs](https://scikit-learn.org/stable/) • [Examples](https://scikit-learn.org/stable/auto_examples/index.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/scikit) |
58-
| **OpenVINO** | 2024.6.0 | Intel's high-performance AI inference toolkit | ✅ 1.82GB | ❌ Execution issues | Computer vision, inference | [Docs](https://docs.openvino.ai/) • [Tutorial](https://docs.openvino.ai/2023.3/notebooks/004-hello-detection-with-output.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/openvino) |
59-
| **NumPy** | 2.0.2 | Fundamental package for scientific computing | ✅ 1.25GB | ✅ 1.08GB | Scientific computing, data analysis | [Docs](https://numpy.org/doc/) • [User Guide](https://numpy.org/doc/stable/user/index.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/numpy) |
60-
| **Matplotlib** | 3.9.4 | Comprehensive library for data visualization | ✅ 1.25GB | ✅ 1.08GB | Data visualization, plotting | [Docs](https://matplotlib.org/) • [Gallery](https://matplotlib.org/stable/gallery/index.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/matplotlib) |
72+
| Framework | Version | Description | TDX Support | SGX Support | Use Cases | Resources |
73+
| ---------------- | ----------- | --------------------------------------------- | ----------- | ------------------- | -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
74+
| **TensorFlow** | 2.19.0 | Google's ML framework for production AI | ✅ 3.01GB | ❌ Too large | Deep learning, CV, NLP | [Docs](https://www.tensorflow.org/) • [Quickstart](https://www.tensorflow.org/tutorials/quickstart/beginner) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/tensorflow) |
75+
| **PyTorch** | 2.7.0+cu126 | Facebook's research-focused DL framework | ✅ 6.44GB | ❌ Too large | Research, DL, CV, NLP | [Docs](https://pytorch.org/docs/) • [Quickstart](https://docs.pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/pytorch) |
76+
| **Scikit-learn** | 1.6.1 | Comprehensive ML library for Python | ✅ 1.18GB | ✅ 1.01GB | Classification, regression, clustering | [Docs](https://scikit-learn.org/stable/) • [Examples](https://scikit-learn.org/stable/auto_examples/index.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/scikit) |
77+
| **OpenVINO** | 2024.6.0 | Intel's high-performance AI inference toolkit | ✅ 1.82GB | ❌ Execution issues | Computer vision, inference | [Docs](https://docs.openvino.ai/) • [Tutorial](https://docs.openvino.ai/2023.3/notebooks/004-hello-detection-with-output.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/openvino) |
78+
| **NumPy** | 2.0.2 | Fundamental package for scientific computing | ✅ 1.25GB | ✅ 1.08GB | Scientific computing, data analysis | [Docs](https://numpy.org/doc/) • [User Guide](https://numpy.org/doc/stable/user/index.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/numpy) |
79+
| **Matplotlib** | 3.9.4 | Comprehensive library for data visualization | ✅ 1.25GB | ✅ 1.08GB | Data visualization, plotting | [Docs](https://matplotlib.org/) • [Gallery](https://matplotlib.org/stable/gallery/index.html) • [Docker](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world/tree/main/matplotlib) |
6180

6281
## 🐳 Getting Started with Docker Examples
6382

6483
### What's Included
65-
Our [AI Frameworks Hello World repository](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world) provides ready-to-use examples:
84+
85+
Our
86+
[AI Frameworks Hello World repository](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world)
87+
provides ready-to-use examples:
6688

6789
```
6890
ai-frameworks-hello-world/
@@ -75,6 +97,7 @@ ai-frameworks-hello-world/
7597
```
7698

7799
### Quick Start Commands
100+
78101
```bash
79102
# Clone the repository
80103
git clone https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world.git
@@ -92,6 +115,7 @@ docker run --rm hello-pytorch
92115
```
93116

94117
### Features
118+
95119
- **✅ Isolated Testing**: Each framework runs in its own container
96120
- **✅ Reproducible**: Consistent environment across systems
97121
- **✅ TDX Ready**: All containers tested for Intel TDX compatibility
@@ -101,38 +125,50 @@ docker run --rm hello-pytorch
101125

102126
### TDX vs SGX for AI
103127

104-
| Feature | Intel TDX | Intel SGX |
105-
|---------|-----------|-----------|
106-
| **Memory Limit** | Multi-GB+ | ~1.95GB |
107-
| **Framework Support** | All major frameworks | Limited (Scikit-learn, NumPy) |
108-
| **Code Changes** | Minimal ("lift and shift") | Significant modifications required |
109-
| **Production Ready** | ✅ Yes | ⚠️ Limited |
110-
| **AI Workloads** | ✅ Excellent | ❌ Restricted |
128+
| Feature | Intel TDX | Intel SGX |
129+
| --------------------- | -------------------------- | ---------------------------------- |
130+
| **Memory Limit** | Multi-GB+ | ~1.95GB |
131+
| **Framework Support** | All major frameworks | Limited (Scikit-learn, NumPy) |
132+
| **Code Changes** | Minimal ("lift and shift") | Significant modifications required |
133+
| **Production Ready** | ✅ Yes | ⚠️ Limited |
134+
| **AI Workloads** | ✅ Excellent | ❌ Restricted |
111135

112136
### Recommendations
113137

114138
#### For Production AI Applications
139+
115140
- **Use TDX** for TensorFlow, PyTorch, and OpenVINO
116141
- **Use SGX** for lightweight ML with Scikit-learn and NumPy
117142

118143
#### For Development and Testing
144+
119145
- **Start with SGX** for simple ML tasks
120146
- **Migrate to TDX** for complex AI workloads
121147

122-
123148
## 📚 Next Steps
124149

125150
### Learn TEE Technologies
126-
- **[Intel SGX Technology](/get-started/protocol/tee/intel-sgx)** - SGX limitations and capabilities
127-
- **[Intel TDX Technology](/get-started/protocol/tee/intel-tdx)** - TDX advantages for AI
128-
- **[SGX vs TDX Comparison](/get-started/protocol/tee/sgx-vs-tdx)** - Detailed comparison
151+
152+
- **[Intel SGX Technology](/get-started/protocol/tee/intel-sgx)** - SGX
153+
limitations and capabilities
154+
- **[Intel TDX Technology](/get-started/protocol/tee/intel-tdx)** - TDX
155+
advantages for AI
156+
- **[SGX vs TDX Comparison](/get-started/protocol/tee/sgx-vs-tdx)** - Detailed
157+
comparison
129158

130159
### Build AI Applications
131-
- **[Build & Deploy](/guides/build-iapp/build-&-deploy)** - Create your first AI application
132-
- **[Build Intel TDX App](/guides/build-iapp/advanced/create-your-first-tdx-app)** - TDX applications for AI workloads
133-
- **[Inputs and Outputs](/guides/build-iapp/inputs-and-outputs)** - Handle data flow in TEE environment
160+
161+
- **[Build & Deploy](/guides/build-iapp/build-&-deploy)** - Create your first AI
162+
application
163+
- **[Build Intel TDX App](/guides/build-iapp/advanced/create-your-first-tdx-app)** -
164+
TDX applications for AI workloads
165+
- **[Inputs and Outputs](/guides/build-iapp/inputs-and-outputs)** - Handle data
166+
flow in TEE environment
134167

135168
### Explore Examples
136-
- **[AI Frameworks Hello World](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world)** - Ready-to-use Docker examples
169+
170+
- **[AI Frameworks Hello World](https://github.com/iExecBlockchainComputing/ai-frameworks-hello-world)** -
171+
Ready-to-use Docker examples
137172
- **[iExec Discord](https://discord.com/invite/pbt9m98wnU)** - Community support
138-
- **[Protocol Documentation](https://protocol.docs.iex.ec)** - Technical deep dive
173+
- **[Protocol Documentation](https://protocol.docs.iex.ec)** - Technical deep
174+
dive

0 commit comments

Comments
 (0)