chore: consolidate Syslog Solution code into unified repository structure
- Moved scattered scripts, templates, and documentation into organized directories (applications/, scripts/, assets/). - Updated .gitignore to strictly exclude secrets, state files, and IDE configs. - Added comprehensive README.md outlining repository structure and best practices. - Preserved all existing documentation and technical architecture files. - Prepared infrastructure/ for AWS Org and Proxmox Terraform management.
This commit is contained in:
@@ -1,223 +0,0 @@
|
||||
# 02 - Technical Architecture
|
||||
|
||||
## 🏗️ Overview
|
||||
This section contains the technical architecture, infrastructure design, deployment standards, and technical documentation for Syslog Solution LLC.
|
||||
|
||||
## 📁 Structure
|
||||
|
||||
```
|
||||
02-technical-architecture/
|
||||
├── README.md # This file
|
||||
├── infrastructure-overview/ # High-level architecture diagrams
|
||||
├── aws-architecture/ # AWS-specific designs and patterns
|
||||
├── proxmox-cluster/ # Homelab infrastructure documentation
|
||||
├── ai-agents-framework/ # AI agent design and implementation
|
||||
├── deployment-standards/ # Deployment procedures and best practices
|
||||
├── security-compliance/ # Security policies and compliance
|
||||
└── monitoring-logging/ # Monitoring, alerting, and logging
|
||||
```
|
||||
|
||||
## 🎯 Architecture Principles
|
||||
|
||||
### Core Principles
|
||||
1. **Automation First** - Everything that can be automated should be automated
|
||||
2. **Infrastructure as Code** - All infrastructure defined in version-controlled code
|
||||
3. **Security by Design** - Security integrated from the beginning, not as an afterthought
|
||||
4. **Scalability** - Systems designed to scale with business growth
|
||||
5. **Cost Optimization** - Efficient use of resources without compromising quality
|
||||
6. **Disaster Recovery** - Built-in redundancy and recovery capabilities
|
||||
|
||||
### Technology Stack
|
||||
|
||||
#### Cloud Infrastructure
|
||||
- **Primary Cloud**: AWS (Amazon Web Services)
|
||||
- **Secondary Cloud**: Proxmox Homelab (for development/testing)
|
||||
- **Container Orchestration**: Docker, Docker Compose
|
||||
- **Infrastructure as Code**: Terraform, Ansible
|
||||
|
||||
#### AI & Automation
|
||||
- **AI Frameworks**: LangChain, LlamaIndex, AutoGen
|
||||
- **Model Providers**: AWS Bedrock, OpenAI, Anthropic, Local models
|
||||
- **Orchestration**: Hermes Agent, Custom multi-agent systems
|
||||
- **Vector Databases**: Pinecone, Chroma, FAISS
|
||||
|
||||
#### Development & Deployment
|
||||
- **Programming Languages**: Python, JavaScript/TypeScript, Bash
|
||||
- **Web Frameworks**: FastAPI, React, Next.js
|
||||
- **CI/CD**: GitHub Actions, AWS CodePipeline
|
||||
- **Monitoring**: Prometheus, Grafana, CloudWatch
|
||||
|
||||
## 🏢 Infrastructure Overview
|
||||
|
||||
### AWS Organization Structure
|
||||
```
|
||||
AWS Organization (Root)
|
||||
├── Management OU
|
||||
│ ├── Management Account (Tier 0)
|
||||
│ └── IAM Identity Center
|
||||
├── Security OU
|
||||
│ ├── Security Account (Tier 0)
|
||||
│ └── Log Archive Account
|
||||
├── Workloads OU
|
||||
│ ├── Development Account (Tier 1)
|
||||
│ ├── Staging Account (Tier 1)
|
||||
│ └── Production Account (Tier 1)
|
||||
└── Sandbox OU
|
||||
└── Sandbox Account (Tier 2)
|
||||
```
|
||||
|
||||
### Proxmox Homelab
|
||||
- **Primary Node**: hwpve (HP Z640)
|
||||
- **Secondary Node**: acerpve (Acer workstation)
|
||||
- **Tertiary Node**: minipve (Mini PC)
|
||||
- **Storage**: PBS (Proxmox Backup Server)
|
||||
- **Purpose**: Development, testing, proof-of-concepts
|
||||
|
||||
### Network Architecture
|
||||
- **VPC Design**: Multi-AZ, public/private subnets
|
||||
- **Security Groups**: Least privilege access
|
||||
- **Network ACLs**: Additional layer of security
|
||||
- **VPN/Connectivity**: Site-to-site VPN for hybrid cloud
|
||||
|
||||
## 🤖 AI Agents Framework
|
||||
|
||||
### Multi-Agent System Architecture
|
||||
```
|
||||
┌─────────────────┐
|
||||
│ Orchestrator │
|
||||
│ (Hermes) │
|
||||
└────────┬────────┘
|
||||
│
|
||||
┌────────┴────────┐
|
||||
│ Specialized │
|
||||
│ Agents │
|
||||
├─────────────────┤
|
||||
│ • Research Agent│
|
||||
│ • Coding Agent │
|
||||
│ • Data Agent │
|
||||
│ • QA Agent │
|
||||
│ • Deploy Agent │
|
||||
└─────────────────┘
|
||||
```
|
||||
|
||||
### Agent Capabilities
|
||||
1. **Research Agent** - Market research, competitor analysis
|
||||
2. **Coding Agent** - Software development, code review
|
||||
3. **Data Agent** - Data analysis, visualization, ETL
|
||||
4. **QA Agent** - Testing, validation, quality assurance
|
||||
5. **Deploy Agent** - Deployment, monitoring, maintenance
|
||||
|
||||
### RAG (Retrieval Augmented Generation)
|
||||
- **Document Indexing**: Company knowledge base, client documentation
|
||||
- **Vector Storage**: Pinecone for production, Chroma for development
|
||||
- **Retrieval**: Semantic search with hybrid search (keyword + vector)
|
||||
- **Generation**: Context-aware responses using LLMs
|
||||
|
||||
## 🚀 Deployment Standards
|
||||
|
||||
### Development Workflow
|
||||
1. **Local Development** → Docker Compose for local testing
|
||||
2. **Code Review** → GitHub Pull Requests with automated checks
|
||||
3. **Staging Deployment** → Automated deployment to staging environment
|
||||
4. **Testing** → Automated tests + manual validation
|
||||
5. **Production Deployment** → Blue-green deployment with rollback
|
||||
|
||||
### Infrastructure Deployment
|
||||
```bash
|
||||
# 1. Initialize Terraform
|
||||
terraform init
|
||||
|
||||
# 2. Plan changes
|
||||
terraform plan -out=tfplan
|
||||
|
||||
# 3. Apply changes (after approval)
|
||||
terraform apply tfplan
|
||||
|
||||
# 4. Verify deployment
|
||||
./scripts/verify-deployment.sh
|
||||
```
|
||||
|
||||
### Application Deployment
|
||||
```bash
|
||||
# 1. Build container
|
||||
docker build -t app:latest .
|
||||
|
||||
# 2. Push to registry
|
||||
docker push registry.sysloggh.com/app:latest
|
||||
|
||||
# 3. Deploy to Kubernetes/ECS
|
||||
./scripts/deploy-app.sh
|
||||
```
|
||||
|
||||
## 🔒 Security & Compliance
|
||||
|
||||
### Security Controls
|
||||
1. **Identity & Access Management**
|
||||
- IAM users with MFA requirement
|
||||
- Role-based access control (RBAC)
|
||||
- Least privilege principle
|
||||
- Regular access reviews
|
||||
|
||||
2. **Data Protection**
|
||||
- Encryption at rest and in transit
|
||||
- Secure key management (AWS KMS)
|
||||
- Data classification and handling
|
||||
- Backup and recovery procedures
|
||||
|
||||
3. **Network Security**
|
||||
- VPC with security groups and NACLs
|
||||
- Web Application Firewall (WAF)
|
||||
- DDoS protection
|
||||
- VPN for secure access
|
||||
|
||||
### Compliance Framework
|
||||
- **GDPR** - Data protection for EU citizens
|
||||
- **ISO 27001** - Information security management
|
||||
- **SOC 2** - Security, availability, processing integrity
|
||||
- **Local Regulations** - Ghana data protection laws
|
||||
|
||||
## 📊 Monitoring & Observability
|
||||
|
||||
### Monitoring Stack
|
||||
- **Infrastructure Monitoring**: CloudWatch, Prometheus
|
||||
- **Application Monitoring**: Application Insights, OpenTelemetry
|
||||
- **Log Management**: CloudWatch Logs, ELK Stack
|
||||
- **Alerting**: SNS, PagerDuty, Telegram bots
|
||||
|
||||
### Key Metrics
|
||||
1. **Availability** - Uptime percentage, error rates
|
||||
2. **Performance** - Response times, throughput
|
||||
3. **Cost** - Cloud spend, cost optimization opportunities
|
||||
4. **Security** - Vulnerability scans, compliance status
|
||||
|
||||
### Incident Response
|
||||
1. **Detection** - Automated alerts trigger incident
|
||||
2. **Response** - Designated team member investigates
|
||||
3. **Resolution** - Fix applied and verified
|
||||
4. **Post-Mortem** - Root cause analysis and prevention
|
||||
|
||||
## 📋 Key Documents
|
||||
|
||||
### Required Documents
|
||||
- [ ] Infrastructure Architecture Diagrams
|
||||
- [ ] Deployment Runbooks
|
||||
- [ ] Security Policy Document
|
||||
- [ ] Disaster Recovery Plan
|
||||
- [ ] Capacity Planning Guide
|
||||
- [ ] Cost Optimization Strategy
|
||||
|
||||
### Status Tracking
|
||||
- **Last Updated**: April 2026
|
||||
- **Next Review**: May 2026
|
||||
- **Owner**: Jerome Tabiri
|
||||
- **Version**: 1.0
|
||||
|
||||
## 🔗 Related Sections
|
||||
- **Business Strategy** → Why we build these systems
|
||||
- **Operations** → How we maintain and support
|
||||
- **Customer Portal** → Client-facing technical documentation
|
||||
- **Development** → Implementation details and coding standards
|
||||
|
||||
---
|
||||
|
||||
*This documentation is proprietary to Syslog Solution LLC. Unauthorized distribution prohibited.*
|
||||
-70
@@ -1,70 +0,0 @@
|
||||
1|# 04 - Autonomous AI Agents — Home
|
||||
2|**Purpose:** Research and implementation of autonomous agent workflows.
|
||||
3|
|
||||
4|## Overview
|
||||
5|
|
||||
6|Autonomous AI agents can execute multi-step tasks independently, learn from experience, and make decisions based on context. This section covers advanced orchestration patterns for production-grade agent systems.
|
||||
7|
|
||||
8|## Key Capabilities
|
||||
9|
|
||||
10|### **Multi-Agent Collaboration**
|
||||
11|- Role-based agent delegation
|
||||
12|- Cross-agent memory sharing
|
||||
13|- Conflict resolution protocols
|
||||
14|- Distributed task execution
|
||||
15|
|
||||
16|### **Autonomous Behaviors**
|
||||
17|- Self-correction loops
|
||||
18|- Error recovery mechanisms
|
||||
19|- Performance optimization
|
||||
20|- Adaptive resource allocation
|
||||
21|
|
||||
22|### **Advanced Patterns**
|
||||
23|- Agent swarms (10+ coordinated agents)
|
||||
24|- Continuous learning cycles
|
||||
25|- Human-in-the-loop intervention points
|
||||
26|- Audit trails and observability
|
||||
27|
|
||||
28|## Implementation Strategies
|
||||
29|
|
||||
30|### **Sequential Workflows**
|
||||
31|```python
|
||||
32|agent1.run(task="Research market")
|
||||
33|agent2.run(task="Analyze data")
|
||||
34|agent3.run(task="Generate report")
|
||||
35|```
|
||||
36|
|
||||
37|### **Parallel Workflows**
|
||||
38|```python
|
||||
39|results = await asyncio.gather(
|
||||
40| agent1.run(task="A"),
|
||||
41| agent2.run(task="B"),
|
||||
42| agent3.run(task="C")
|
||||
43|)
|
||||
44|```
|
||||
45|
|
||||
46|### **Feedback Loops**
|
||||
47|```python
|
||||
48|while not agent.is_satisfied(result):
|
||||
49| agent.improve(result)
|
||||
50| result = agent.execute(prompt)
|
||||
51|```
|
||||
52|
|
||||
53|## Use Cases
|
||||
54|
|
||||
55|- Market research automation
|
||||
56|- Multi-step data analysis pipelines
|
||||
57|- Customer support orchestration
|
||||
58|- Content generation workflows
|
||||
59|- Codebase refactoring agents
|
||||
60|
|
||||
61|## Related Frameworks
|
||||
62|
|
||||
63|- **[OpenClaw](../02\ -\ OpenClaw\ Framework/)** — Agent orchestration platform
|
||||
64|- **[MCP](../03\ -\ MCP\ \(Model\ Context\ Protocol\)/)** — Tool integration layer
|
||||
65|- **[OpenMAIC](../06\ -\ OpenMAIC\ Education/)** — Educational resources
|
||||
66|
|
||||
67|---
|
||||
68|
|
||||
69|*Advanced agent patterns for Jerome & Theodore's complex automation projects.*
|
||||
70|
|
||||
-53
@@ -1,53 +0,0 @@
|
||||
1|# 01 - Claude Code & Opencode — Home
|
||||
2|**Purpose:** Agent framework tutorials and best practices for Claude Code and OpenCode CLI.
|
||||
3|
|
||||
4|## Overview
|
||||
5|
|
||||
6|This section provides practical guides for deploying and managing AI coding agents using Claude Code and OpenCode CLI tools.
|
||||
7|
|
||||
8|## Contents
|
||||
9|
|
||||
10|### **Claude Code**
|
||||
11|- Quick start and configuration
|
||||
12|- Integration with IDEs
|
||||
13|- Custom agent definitions
|
||||
14|- Security best practices
|
||||
15|
|
||||
16|### **OpenCode**
|
||||
17|- CLI setup and usage
|
||||
18|- Extending with custom commands
|
||||
19|- Multi-agent orchestration
|
||||
20|- Production deployment patterns
|
||||
21|
|
||||
22|### **Best Practices**
|
||||
23|- Context window management
|
||||
24|- Agent sandboxing rules
|
||||
25|- Error handling patterns
|
||||
26|- Performance optimization
|
||||
27|
|
||||
28|## Quick Start
|
||||
29|
|
||||
30|```bash
|
||||
31|# Install OpenCode CLI
|
||||
32|pip install opencode-cli
|
||||
33|
|
||||
34|# Configure API keys
|
||||
35|export OPENAI_API_KEY="***"
|
||||
36|
|
||||
37|# Run Claude Code
|
||||
38|opencode run "Analyze this codebase for security issues"
|
||||
39|
|
||||
40|# Create custom agent
|
||||
41|opencode agent create --name my-helper --template best-practices
|
||||
42|```
|
||||
43|
|
||||
44|## Related Frameworks
|
||||
45|
|
||||
46|- **[MCP (Model Context Protocol)](../03\ -\ MCP\ \(Model\ Context\ Protocol\)/)** — Tool integration
|
||||
47|- **[OpenClaw Framework](../02\ -\ OpenClaw\ Framework/)** — Multi-agent orchestration
|
||||
48|- **[Autonomous AI Agents](../04\ -\ Autonomous\ AI\ Agents/)** — Advanced workflows
|
||||
49|
|
||||
50|---
|
||||
51|
|
||||
52|*Practical guides for Jerome & Theodore to implement AI coding agents in their daily workflow.*
|
||||
53|
|
||||
@@ -1,87 +0,0 @@
|
||||
1|# 02 - MCP (Model Context Protocol) — Home
|
||||
2|**Purpose:** MCP integration guides and implementation examples.
|
||||
3|
|
||||
4|## What is MCP?
|
||||
5|Model Context Protocol (MCP) is a standardized interface for connecting LLMs to external tools, data sources, and services.
|
||||
6|
|
||||
7|## MCP Benefits
|
||||
8|- **Unified interface** for tool integration
|
||||
9|- **Hot-swappable** tool providers
|
||||
10|- **Standardized** input/output schemas
|
||||
11|- **Type-safe** API definitions
|
||||
12|
|
||||
13|## Core Concepts
|
||||
14|
|
||||
15|### Tools
|
||||
16|External capabilities exposed to the model:
|
||||
17|- File system access
|
||||
18|- Database queries
|
||||
19|- API endpoints
|
||||
20|- Custom business logic
|
||||
21|
|
||||
22|### Resources
|
||||
23|Data sources the model can read:
|
||||
24|- Documents
|
||||
25|- Configuration files
|
||||
26|- Real-time data feeds
|
||||
27|- Knowledge bases
|
||||
28|
|
||||
29|### Prompts
|
||||
30|Pre-defined interaction templates:
|
||||
31|- Task initiation patterns
|
||||
32|- System prompt variations
|
||||
33|- Role-definition templates
|
||||
34|
|
||||
35|## Quick Start
|
||||
36|
|
||||
37|```bash
|
||||
38|# Install MCP server
|
||||
39|pip install mcp-server-filesystem mcp-server-sqlite
|
||||
40|
|
||||
41|# Start a filesystem MCP server
|
||||
42|mcp-server-filesystem --path /path/to/allowed/directory
|
||||
43|
|
||||
44|# Connect via client
|
||||
45|from mcp import ClientSession, StdioServerParameters
|
||||
46|
|
||||
47|async with ClientSession(
|
||||
48| stdio_server_parameters=StdioServerParameters(
|
||||
49| command="mcp-server-filesystem",
|
||||
50| args=["--path", "/path/to/allowed/directory"]
|
||||
51| )
|
||||
52|) as session:
|
||||
53| # List available tools
|
||||
54| tools = await session.list_tools()
|
||||
55|```
|
||||
56|
|
||||
57|## Available MCP Servers
|
||||
58|
|
||||
59|- **Filesystem:** Access documents and configuration files
|
||||
60|- **SQL databases:** Query relational databases safely
|
||||
61|- **API Gateway:** Connect to REST/GraphQL endpoints
|
||||
62|- **Custom Business Logic:** Integrate internal tools and services
|
||||
63|
|
||||
64|## Security Considerations
|
||||
65|
|
||||
66|- **Path whitelisting:** Only allow specific directories
|
||||
67|- **Query rate limiting:** Prevent resource exhaustion
|
||||
68|- **Input sanitization:** Validate all user inputs
|
||||
69|- **Token-based access:** Require authentication for sensitive operations
|
||||
70|
|
||||
71|## Use Cases
|
||||
72|
|
||||
73|- **Document analysis:** Read and process large document collections
|
||||
74|- **Database queries:** Extract insights from operational databases
|
||||
75|- **API orchestration:** Coordinate across multiple external services
|
||||
76|- **Code generation:** Write and execute code safely
|
||||
77|
|
||||
78|## References
|
||||
79|
|
||||
80|- [MCP Specification](https://modelcontextprotocol.io)
|
||||
81|- [MCP Server Implementations](https://github.com/modelcontextprotocol/servers)
|
||||
82|- [Integration Examples](../03%20-%20AI%20AGENTS%20&%20LEARNING/02%20-%20OpenClaw%20Framework/)
|
||||
83|
|
||||
84|---
|
||||
85|
|
||||
86|*MCP integrates seamlessly with OpenClaw agent orchestration for scalable AI applications.*
|
||||
87|
|
||||
-59
@@ -1,59 +0,0 @@
|
||||
1|# OpenClaw Framework — Home
|
||||
2|**Purpose:** Complete guide to setting up and using the OpenClaw agent orchestration framework.
|
||||
3|
|
||||
4|## What is OpenClaw?
|
||||
5|OpenClaw provides a powerful framework for orchestrating AI agents, enabling multi-agent collaboration, task delegation, and complex workflow automation.
|
||||
6|
|
||||
7|## Quick Start
|
||||
8|
|
||||
9|### Installation
|
||||
10|```bash
|
||||
11|# Clone the repository
|
||||
12|git clone https://github.com/openclaw/openclaw.git
|
||||
13|cd openclaw
|
||||
14|
|
||||
15|# Install dependencies
|
||||
16|pip install -r requirements.txt
|
||||
17|
|
||||
18|# Configure API keys
|
||||
19|export OPENCLAW_API_KEY="***"
|
||||
20|```
|
||||
21|
|
||||
22|### Basic Usage
|
||||
23|```python
|
||||
24|from openclaw import AgentOrchestrator
|
||||
25|
|
||||
26|# Create an orchestrator
|
||||
27|orchestrator = AgentOrchestrator()
|
||||
28|
|
||||
29|# Define agent roles
|
||||
30|agents = {
|
||||
31| "researcher": Agent(role="researcher"),
|
||||
32| "analyst": Agent(role="analyst"),
|
||||
33| "writer": Agent(role="writer")
|
||||
34|}
|
||||
35|
|
||||
36|# Run a multi-agent workflow
|
||||
37|result = orchestrator.run_task(
|
||||
38| task="Write market analysis report",
|
||||
39| agents=agents
|
||||
40|)
|
||||
41|```
|
||||
42|
|
||||
43|## Framework Components
|
||||
44|
|
||||
45|- **Agent Registry:** Pool of specialized agents
|
||||
46|- **Task Dispatcher:** Routes tasks to appropriate agents
|
||||
47|- **Collaboration Layer:** Enables agent-to-agent communication
|
||||
48|- **Orchestration Engine:** Coordinates complex workflows
|
||||
49|
|
||||
50|## Use Cases
|
||||
51|
|
||||
52|- Market research automation
|
||||
53|- Content generation pipelines
|
||||
54|- Multi-step data analysis
|
||||
55|- Autonomous decision making
|
||||
56|
|
||||
57|---
|
||||
58|
|
||||
59|*For advanced usage, refer to the Advanced Usage guide and API Reference documentation.*
|
||||
+92
-92
@@ -1,92 +1,92 @@
|
||||
1|# 06 - OpenMAIC Education — Home
|
||||
2|**Purpose:** OpenMAIC (Open Multi-Agent AI Collaboration) educational resources and curriculum.
|
||||
3|
|
||||
4|## What is OpenMAIC?
|
||||
5|
|
||||
6|OpenMAIC (Open Multi-Agent AI Collaboration) is an educational framework designed to help teams understand and implement multi-agent AI systems. It provides:
|
||||
7|
|
||||
8|- **Structured Curriculum:** From fundamentals to advanced patterns
|
||||
9|- **Hands-on Exercises:** Real-world practice through coding challenges
|
||||
10|- **Community Learning:** Collaborative problem-solving and knowledge sharing
|
||||
11|
|
||||
12|## Curriculum Structure
|
||||
13|
|
||||
14|### **Module 1: Fundamentals**
|
||||
15|- Introduction to multi-agent systems
|
||||
16|- Agent role definition and capabilities
|
||||
17|- Basic orchestration patterns
|
||||
18|- Simple agent collaboration examples
|
||||
19|
|
||||
20|### **Module 2: Advanced Collaboration**
|
||||
21|- Complex workflow design
|
||||
22|- Context sharing between agents
|
||||
23|- Error handling and recovery
|
||||
24|- Performance optimization
|
||||
25|
|
||||
26|### **Module 3: Production Patterns**
|
||||
27|- Scaling to 10+ agents
|
||||
28|- Monitoring and diagnostics
|
||||
29|- Security best practices
|
||||
30|- Cost optimization strategies
|
||||
31|
|
||||
32|### **Module 4: Real-World Applications**
|
||||
33|- Market analysis automation
|
||||
34|- Customer support orchestration
|
||||
35|- Content pipeline automation
|
||||
36|- Data processing workflows
|
||||
37|
|
||||
38|## Getting Started
|
||||
39|
|
||||
40|```bash
|
||||
41|# Step 1: Install OpenMAIC
|
||||
42|pip install openmaic-core openmaic-visualizer
|
||||
43|
|
||||
44|# Step 2: Clone learning resources
|
||||
45|git clone https://github.com/sysloggh/openmaic-learning.git
|
||||
46|cd openmaic-learning/modules
|
||||
47|
|
||||
48|# Step 3: Start with Module 1
|
||||
49|python module01_fundamentals.py
|
||||
50|```
|
||||
51|
|
||||
52|## Example Agent Collaboration
|
||||
53|
|
||||
54|```python
|
||||
55|from openmaic.core import Orchestrator, Agent
|
||||
56|
|
||||
57|# Initialize orchestrator
|
||||
58|orchestrator = Orchestrator(
|
||||
59| max_agents=3,
|
||||
60| collaboration_mode="sequential"
|
||||
61|)
|
||||
62|
|
||||
63|# Create agents
|
||||
64|researcher = Agent(name="researcher", role="Research Assistant")
|
||||
65|analyst = Agent(name="analyst", role="Data Analysis")
|
||||
66|writer = Agent(name="writer", role="Content Generator")
|
||||
67|
|
||||
68|# Execute workflow
|
||||
69|result = orchestrator.run([
|
||||
70| researcher.run(task="Research AI trends"),
|
||||
71| analyst.run(task="Analyze market data"),
|
||||
72| writer.run(task="Write market report")
|
||||
73|])
|
||||
74|```
|
||||
75|
|
||||
76|## Use Cases at Syslog GH/LLC
|
||||
77|
|
||||
78|- **Market Research Automation:** Automatically gather and analyze SMB AI adoption data
|
||||
79|- **Content Generation:** Create service descriptions and case studies
|
||||
80|- **Customer Support:** Multi-agent Q&A for client inquiries
|
||||
81|- **Code Review Agents:** Automated code quality checks
|
||||
82|
|
||||
83|## Related Resources
|
||||
84|
|
||||
85|- **[Autonomous AI Agents](../04\ -\ Autonomous\ AI\ Agents/)** — Advanced workflows
|
||||
86|- **[Claude Code & Opencode](../01\ -\ Claude\ Code\ \&\ Opencode/)** — Practical implementation
|
||||
87|- **[MCP (Model Context Protocol)](../03\ -\ MCP\ \(Model\ Context\ Protocol\)/)** — Tool integration
|
||||
88|
|
||||
89|---
|
||||
90|
|
||||
91|*Perfect for Jerome & Theodore's strategy sessions on AI agent frameworks and multi-agent collaboration patterns. This curriculum supports our mission to educate SMBs on AI adoption while building our own agent capabilities.*
|
||||
92|
|
||||
1|# 06 - OpenMAIC Education — Home
|
||||
2|**Purpose:** OpenMAIC (Open Multi-Agent AI Collaboration) educational resources and curriculum.
|
||||
3|
|
||||
4|## What is OpenMAIC?
|
||||
5|
|
||||
6|OpenMAIC (Open Multi-Agent AI Collaboration) is an educational framework designed to help teams understand and implement multi-agent AI systems. It provides:
|
||||
7|
|
||||
8|- **Structured Curriculum:** From fundamentals to advanced patterns
|
||||
9|- **Hands-on Exercises:** Real-world practice through coding challenges
|
||||
10|- **Community Learning:** Collaborative problem-solving and knowledge sharing
|
||||
11|
|
||||
12|## Curriculum Structure
|
||||
13|
|
||||
14|### **Module 1: Fundamentals**
|
||||
15|- Introduction to multi-agent systems
|
||||
16|- Agent role definition and capabilities
|
||||
17|- Basic orchestration patterns
|
||||
18|- Simple agent collaboration examples
|
||||
19|
|
||||
20|### **Module 2: Advanced Collaboration**
|
||||
21|- Complex workflow design
|
||||
22|- Context sharing between agents
|
||||
23|- Error handling and recovery
|
||||
24|- Performance optimization
|
||||
25|
|
||||
26|### **Module 3: Production Patterns**
|
||||
27|- Scaling to 10+ agents
|
||||
28|- Monitoring and diagnostics
|
||||
29|- Security best practices
|
||||
30|- Cost optimization strategies
|
||||
31|
|
||||
32|### **Module 4: Real-World Applications**
|
||||
33|- Market analysis automation
|
||||
34|- Customer support orchestration
|
||||
35|- Content pipeline automation
|
||||
36|- Data processing workflows
|
||||
37|
|
||||
38|## Getting Started
|
||||
39|
|
||||
40|```bash
|
||||
41|# Step 1: Install OpenMAIC
|
||||
42|pip install openmaic-core openmaic-visualizer
|
||||
43|
|
||||
44|# Step 2: Clone learning resources
|
||||
45|git clone https://github.com/sysloggh/openmaic-learning.git
|
||||
46|cd openmaic-learning/modules
|
||||
47|
|
||||
48|# Step 3: Start with Module 1
|
||||
49|python module01_fundamentals.py
|
||||
50|```
|
||||
51|
|
||||
52|## Example Agent Collaboration
|
||||
53|
|
||||
54|```python
|
||||
55|from openmaic.core import Orchestrator, Agent
|
||||
56|
|
||||
57|# Initialize orchestrator
|
||||
58|orchestrator = Orchestrator(
|
||||
59| max_agents=3,
|
||||
60| collaboration_mode="sequential"
|
||||
61|)
|
||||
62|
|
||||
63|# Create agents
|
||||
64|researcher = Agent(name="researcher", role="Research Assistant")
|
||||
65|analyst = Agent(name="analyst", role="Data Analysis")
|
||||
66|writer = Agent(name="writer", role="Content Generator")
|
||||
67|
|
||||
68|# Execute workflow
|
||||
69|result = orchestrator.run([
|
||||
70| researcher.run(task="Research AI trends"),
|
||||
71| analyst.run(task="Analyze market data"),
|
||||
72| writer.run(task="Write market report")
|
||||
73|])
|
||||
74|```
|
||||
75|
|
||||
76|## Use Cases at Syslog GH/LLC
|
||||
77|
|
||||
78|- **Market Research Automation:** Automatically gather and analyze SMB AI adoption data
|
||||
79|- **Content Generation:** Create service descriptions and case studies
|
||||
80|- **Customer Support:** Multi-agent Q&A for client inquiries
|
||||
81|- **Code Review Agents:** Automated code quality checks
|
||||
82|
|
||||
83|## Related Resources
|
||||
84|
|
||||
85|- **[Autonomous AI Agents](../04\ -\ Autonomous\ AI\ Agents/)** — Advanced workflows
|
||||
86|- **[Claude Code & Opencode](../01\ -\ Claude\ Code\ \&\ Opencode/)** — Practical implementation
|
||||
87|- **[MCP (Model Context Protocol)](../03\ -\ MCP\ \(Model\ Context\ Protocol\)/)** — Tool integration
|
||||
88|
|
||||
89|---
|
||||
90|
|
||||
91|*Perfect for Jerome & Theodore's strategy sessions on AI agent frameworks and multi-agent collaboration patterns. This curriculum supports our mission to educate SMBs on AI adoption while building our own agent capabilities.*
|
||||
92|
|
||||
-19
@@ -1,19 +0,0 @@
|
||||
1|# 03 - AI AGENTS & LEARNING — Home
|
||||
2|**Purpose:** AI agent frameworks, learning resources, and implementation guides.
|
||||
3|
|
||||
4|## Contents
|
||||
5|
|
||||
6|### **01 - Claude Code & Opencode** — Agent framework tutorials and best practices.
|
||||
7|
|
||||
8|### **02 - OpenClaw Framework** — Open-source agent orchestration platform setup and usage.
|
||||
9|
|
||||
10|### **03 - MCP (Model Context Protocol)** — Integration guides for connecting LLMs to external tools and data sources.
|
||||
11|
|
||||
12|### **04 - Autonomous AI Agents** — Research and implementation of autonomous agent workflows.
|
||||
13|
|
||||
14|### **05 - Agent Research & Learning** — Papers, YouTube tutorials, podcasts, and general learning resources.
|
||||
15|
|
||||
16|---
|
||||
17|
|
||||
18|*This section pairs conceptual guides with their implementation scripts for rapid prototyping and deployment.*
|
||||
19|
|
||||
-43
@@ -1,43 +0,0 @@
|
||||
1|# 04 - Qwen3.5 Model Setup — Home
|
||||
2|**Purpose:** Installation and configuration guides for Qwen3.5 model variants.
|
||||
3|
|
||||
4|## Available Models
|
||||
5|
|
||||
6|### **Qwen3.5-MoE (Mixture of Experts)** — Optimized for production inference with dynamic expert routing.
|
||||
7|
|
||||
8|### **Qwen3.5-Base** — Standard dense model variant.
|
||||
9|
|
||||
10|### **Qwen3.5-FineTuned** — Domain-specific fine-tuned variants.
|
||||
11|
|
||||
12|## GPU Compatibility
|
||||
13|
|
||||
14|- **AMD Strix Halo** — See [AMD GPU Passthrough Guide](../03\ -\ AMD\ GPU\ Passthrough/00\ -\ AMD\ GPU\ Passthrough.md)
|
||||
15|- **NVIDIA RTX 4090** — Standard CUDA setup
|
||||
16|- **Multi-GPU Clusters** — Distributed inference setup
|
||||
17|
|
||||
18|## Quick Start
|
||||
19|
|
||||
20|### Install Qwen3.5-MoE via Ollama
|
||||
21|```bash
|
||||
22|ollama pull qwen3.5:250b-moe
|
||||
23|ollama serve
|
||||
24|
|
||||
25|# Run locally at 192.168.68.8:8080
|
||||
26|ollama run qwen3.5:250b-moe "What are the top AI trends for 2026?"
|
||||
27|```
|
||||
28|
|
||||
29|### Advanced Configuration
|
||||
30|
|
||||
31|For production deployments with dynamic expert selection:
|
||||
32|- See `/60\ -\ Syslog/02\ -\ TECHNICAL\ INFRASTRUCTURE/04\ -\ Qwen3.5\ Model\ Setup/01\ -\ Qwen3.5-MoE\ Configuration.md`
|
||||
33|- GPU passthrough: `/60\ -\ Syslog/02\ -\ TECHNICAL\ INFRASTRUCTURE/03\ -\ AMD\ GPU\ Passthrough/00\ -\ AMD\ GPU\ Passthrough.md`
|
||||
34|
|
||||
35|## Scripts
|
||||
36|
|
||||
37|- `vulkan-qwen35-moe-setup.sh` — Complete setup script for Qwen3.5-MoE with Vulkan backend
|
||||
38|- `qwen35-moe-inference-config.sh` — Production inference configuration script
|
||||
39|
|
||||
40|---
|
||||
41|
|
||||
42|*For AMD GPU-specific setup, refer to the AMD GPU Passthrough guide.*
|
||||
43|
|
||||
-54
@@ -1,54 +0,0 @@
|
||||
1|# 05 - Agent Research & Learning — Home
|
||||
2|**Purpose:** Research papers, tutorials, and resources for AI agent development.
|
||||
3|
|
||||
4|## Overview
|
||||
5|
|
||||
6|Stay current with the latest developments in AI agent technology through curated research, tutorials, and community resources.
|
||||
7|
|
||||
8|## Learning Resources
|
||||
9|
|
||||
10|### **Academic Papers**
|
||||
11|- **Multi-Agent Systems:** Foundations and applications
|
||||
12|- **Reinforcement Learning for Agents:** Q-learning, PPO, GRPO
|
||||
13|- **Agent Communication Protocols:** FIPA, ACL, custom protocols
|
||||
14|- **Tool Learning:** In-context learning for tool selection
|
||||
15|
|
||||
16|### **Video Tutorials**
|
||||
17|- **YouTube Series:** Deep dives into agent architectures
|
||||
18|- **Conference Keynotes:** NeurIPS, ICML, ICLR talks
|
||||
19|- **Hands-on Labs:** Step-by-step implementation guides
|
||||
20|
|
||||
21|### **Podcasts**
|
||||
22|- **AI Agent Deep Dives:** Interviews with researchers
|
||||
23|- **Industry Applications:** Real-world use cases
|
||||
24|- **Future Trends:** Expert predictions and analysis
|
||||
25|
|
||||
26|### **Community Resources**
|
||||
27|- **GitHub Repositories:** Open-source agent frameworks
|
||||
28|- **Discord Servers:** Community support and collaboration
|
||||
29|- **Conferences:** Annual meetups and workshops
|
||||
30|
|
||||
31|## Recommended Reading
|
||||
32|
|
||||
33|1. **"Language Models as Zero-Shot Planners"** — arXiv:2106.04415
|
||||
34|2. **"ReAct: Synergizing Reasoning and Acting"** — arXiv:2210.03629
|
||||
35|3. **"Tool Learning: LLMs Learning to Call External APIs"** — arXiv:2302.04762
|
||||
36|4. **"Multi-Agent Collaboration: A Survey"** — arXiv:2310.08056
|
||||
37|
|
||||
38|## Stay Updated
|
||||
39|
|
||||
40|- **arXiv Alerts:** Set up daily/weekly digests for "agent" papers
|
||||
41|- **Twitter/X:** Follow key researchers and AI labs
|
||||
42|- **GitHub Topics:** #ai-agents, #multi-agent, #agent-orchestration
|
||||
43|- **Newsletter:** AI Weekly, Towards Data Science, ML News
|
||||
44|
|
||||
45|## Related Frameworks
|
||||
46|
|
||||
47|- **[Claude Code & Opencode](../01\ -\ Claude\ Code\ \&\ Opencode/)** — Practical implementation
|
||||
48|- **[OpenClaw Framework](../02\ -\ OpenClaw\ Framework/)** — Production orchestration
|
||||
49|- **[OpenMAIC Education](../06\ -\ OpenMAIC\ Education/)** — Structured learning
|
||||
50|
|
||||
51|---
|
||||
52|
|
||||
53|*Continuous learning resources for Jerome & Theodore to stay ahead in AI agent development.*
|
||||
54|
|
||||
@@ -1,44 +0,0 @@
|
||||
1|# 05 - AWS Cloud Infrastructure — Home
|
||||
2|**Purpose:** AWS architecture, networking, and cost optimization for AI workloads.
|
||||
3|
|
||||
4|## Overview
|
||||
5|
|
||||
6|This section covers our AWS cloud infrastructure setup for scalable AI services, including:
|
||||
7|- VPC networking architecture
|
||||
8|- EC2 instance optimization for GPU workloads
|
||||
9|- S3 data pipeline automation
|
||||
10|- Cost optimization strategies
|
||||
11|
|
||||
12|## Infrastructure Components
|
||||
13|
|
||||
14|### **AWS Architecture**
|
||||
15|- **US-East-1 (N. Virginia):** Primary production environment
|
||||
16|- **Multi-AZ deployment:** High availability for critical services
|
||||
17|- **VPC networking:** Isolated subnets for compute, storage, and monitoring
|
||||
18|
|
||||
19|### **Compute Resources**
|
||||
20|- **p4d.24xlarge:** A100-based instances for training
|
||||
21|- **g5.xlarge:** A10 instances for inference
|
||||
22|- **m5.large:** CPU-based instances for web services
|
||||
23|- **Spot instances:** Cost savings for non-critical workloads
|
||||
24|
|
||||
25|### **Storage**
|
||||
26|- **S3 buckets:** Model weights, datasets, backup archives
|
||||
27|- **EBS volumes:** High-performance storage for active VMs
|
||||
28|- **Glacier:** Cold storage for historical data
|
||||
29|
|
||||
30|## Cost Optimization
|
||||
31|
|
||||
32|- **Reserved Instances:** 1-3 year commitments for baseline workloads
|
||||
33|- **Spot Instances:** 70% savings for fault-tolerant tasks
|
||||
34|- **S3 Lifecycle Policies:** Automatic tiering to Glacier
|
||||
35|- **CloudWatch Alarms:** Budget alerts and anomaly detection
|
||||
36|
|
||||
37|## Related Documents
|
||||
38|
|
||||
39|- **[Qwen3.5-MoE Setup](../02\ -\ TECHNICAL\ INFRASTRUCTURE/04\ -\ Qwen3.5\ Model\ Setup/)** — Model deployment strategies
|
||||
40|
|
||||
41|---
|
||||
42|
|
||||
43|*Our AWS infrastructure supports our SMB AI services and agent deployments with maximum efficiency.*
|
||||
44|
|
||||
-86
@@ -1,86 +0,0 @@
|
||||
1|# 02 - TECHNICAL INFRASTRUCTURE — Overview
|
||||
2|**Purpose:** Complete technical guide for Syslog infrastructure, GPU passthrough, and model deployment.
|
||||
3|
|
||||
4|## Infrastructure Components
|
||||
5|
|
||||
6|### **01 - Proxmox & VM Passthrough**
|
||||
7|- GPU passthrough configuration (AMD/Intel)
|
||||
8|- VM networking setup
|
||||
9|- Resource allocation best practices
|
||||
10|
|
||||
11|### **02 - GPU Monitoring**
|
||||
12|- Grafana dashboards for GPU telemetry
|
||||
13|- ROCm monitoring setup
|
||||
14|- Real-time performance tracking
|
||||
15|
|
||||
16|### **03 - AMD GPU Passthrough (Strix Halo)**
|
||||
17|- Detailed AMD APU passthrough for host LLM access
|
||||
18|- Vulkan driver configuration
|
||||
19|- HIP SDK integration
|
||||
20|
|
||||
21|### **04 - Qwen3.5 Model Setup**
|
||||
22|- Qwen3.5-MoE (Mixture of Experts) installation
|
||||
23|- Vulkan backend optimization
|
||||
24|- Production inference configuration
|
||||
25|
|
||||
26|### **05 - AWS Cloud Infrastructure**
|
||||
27|- VPC and networking architecture
|
||||
28|- EC2 instance configuration for AI workloads
|
||||
29|- S3 data pipeline setup
|
||||
30|- Cost optimization strategies
|
||||
31|
|
||||
32|## Deployment Standards
|
||||
33|
|
||||
34|- **GPU Access:** AMD Strix Halo for host inference, NVIDIA for training
|
||||
35|- **Model Hosting:** Ollama local deployment @ 192.168.68.8:8080
|
||||
36|- **Cloud:** AWS for scalable cloud workloads
|
||||
37|- **Storage:** S3 for model weights and datasets
|
||||
38|- **Monitoring:** Grafana + Prometheus for observability
|
||||
39|
|
||||
40|## Common Operations
|
||||
41|
|
||||
42|### Start Qwen3.5-MoE
|
||||
43|```bash
|
||||
44|ollama pull qwen3.5:250b-moe
|
||||
45|ollama serve --model qwen3.5:250b-moe
|
||||
46|```
|
||||
47|
|
||||
48|### Check GPU Status
|
||||
49|```bash
|
||||
50|# AMD
|
||||
51|rocm-smi
|
||||
52|watch -n 5 rocm-smi
|
||||
53|
|
||||
54|# NVIDIA
|
||||
55|nvidia-smi
|
||||
56|watch -n 5 nvidia-smi
|
||||
57|```
|
||||
58|
|
||||
59|### Deploy New Agent
|
||||
60|```bash
|
||||
61|# Clone agent repository
|
||||
62|git clone https://github.com/sysloggh/agent-template.git
|
||||
63|cd agent-template
|
||||
64|
|
||||
65|# Configure environment
|
||||
66|cp .env.example .env
|
||||
67|# Edit .env with API keys and settings
|
||||
68|
|
||||
69|# Install dependencies
|
||||
70|pip install -r requirements.txt
|
||||
71|
|
||||
72|# Deploy
|
||||
73|source venv/bin/activate
|
||||
74|python main.py
|
||||
75|```
|
||||
76|
|
||||
77|## Related Documentation
|
||||
78|
|
||||
79|- [Business Strategy](../01\ -\ BUSINESS\ \&\ STRATEGY/00\ -\ Business Strategy Home.md)
|
||||
80|- [AI Agents Framework](../03\ -\ AI\ AGENTS\ \&\ LEARNING/00\ -\ AI Agents Learning Home.md)
|
||||
81|- [Operational Excellence](../05\ -\ OPERATIONAL\ EXCELLENCE/00\ -\ Operational Excellence Home.md)
|
||||
82|
|
||||
83|---
|
||||
84|
|
||||
85|*This section pairs implementation guides with their respective scripts for rapid deployment.*
|
||||
86|
|
||||
@@ -1,51 +0,0 @@
|
||||
1|# 02 - GPU Monitoring — Home
|
||||
2|**Purpose:** Grafana dashboards and monitoring setup for GPU telemetry.
|
||||
3|
|
||||
4|## Contents
|
||||
5|
|
||||
6|This directory contains:
|
||||
7|- Grafana dashboard configuration
|
||||
8|- ROCm monitoring setup
|
||||
9|- Real-time performance tracking
|
||||
10|
|
||||
11|### Monitoring Features
|
||||
12|
|
||||
13|- **Real-time GPU utilization:** Track VRAM, compute, and memory usage
|
||||
14|- **Temperature monitoring:** Alert on overheating conditions
|
||||
15|- **Performance metrics:** Core clock, power consumption, fan speeds
|
||||
16|- **Historical data:** Grafana time-series graphs for trend analysis
|
||||
17|
|
||||
18|## Quick Start
|
||||
19|
|
||||
20|### Grafana Dashboard Setup
|
||||
21|
|
||||
22|```bash
|
||||
23|# Install Grafana
|
||||
24|sudo apt install grafana
|
||||
25|
|
||||
26|# Start Grafana service
|
||||
27|systemctl start grafana-server
|
||||
28|
|
||||
29|# Access dashboard
|
||||
30|# http://localhost:3000 (admin/admin)
|
||||
31|```
|
||||
32|
|
||||
33|### ROCm Monitoring
|
||||
34|
|
||||
35|```bash
|
||||
36|# Install ROCm health monitoring tools
|
||||
37|sudo apt install rocminfo rocm-smi
|
||||
38|
|
||||
39|# Real-time monitoring
|
||||
40|watch -n 1 rocm-smi
|
||||
41|```
|
||||
42|
|
||||
43|## Related Infrastructure
|
||||
44|
|
||||
45|- **[AMD GPU Passthrough](../03\ -\ AMD\ GPU\ Passthrough/)** — Hardware configuration
|
||||
46|- **[Qwen3.5 Model Setup](../04\ -\ Qwen3.5\ Model\ Setup/)** — Model deployment
|
||||
47|
|
||||
48|---
|
||||
49|
|
||||
50|*Monitor your GPUs 24/7 to ensure optimal performance for LLM inference workloads.*
|
||||
51|
|
||||
-47
@@ -1,47 +0,0 @@
|
||||
1|# 01 - Proxmox & VM Passthrough — Home
|
||||
2|**Purpose:** Complete setup guide for Proxmox VM passthrough with optimal resource allocation.
|
||||
3|
|
||||
4|## Topics Covered
|
||||
5|
|
||||
6|- **GPU Passthrough:** Configure AMD/Intel/NVIDIA GPUs for VM access
|
||||
7|- **NVMe Passthrough:** Pass NVMe drives to VMs for high I/O performance
|
||||
8|- **USB Passthrough:** Connect USB devices (webcams, dongles, etc.) to VMs
|
||||
9|- **Networking:** Bridge networking, VLANs, and virtual switches
|
||||
10|- **Resource Allocation:** CPU cores, RAM, and storage optimization
|
||||
11|
|
||||
12|## Related Guides
|
||||
13|
|
||||
14|- **[00 - Proxmox & VM Passthrough](00 - Proxmox & VM Passthrough.md)** — This overview document
|
||||
15|- **[03 - AMD GPU Passthrough](../03\ -\ AMD\ GPU\ Passthrough/)** — AMD-specific setup
|
||||
16|
|
||||
17|## Quick Start
|
||||
18|
|
||||
19|### Create a VM with GPU Passthrough
|
||||
20|
|
||||
21|```bash
|
||||
22|# Step 1: Find available GPU
|
||||
23|rocm-smi | grep "GPU" # AMD
|
||||
24|nvidia-smi # NVIDIA
|
||||
25|
|
||||
26|# Step 2: Create VM with GPU passthrough
|
||||
27|qm create 100 --name qwen-vm --memory 32768 --cores 8 --arch x86_64
|
||||
28|qm set 100 --hostpci0=0000:03:00.0,pcie=1,x-vga=1 # AMD example
|
||||
29|
|
||||
30|# Step 3: Install QEMU Guest Agent
|
||||
31|apt install qemu-guest-agent
|
||||
32|
|
||||
33|# Step 4: Reboot VM
|
||||
34|qm reboot 100
|
||||
35|```
|
||||
36|
|
||||
37|## Best Practices
|
||||
38|
|
||||
39|1. **IOMMU Groups:** Always check if devices are in separate IOMMU groups
|
||||
40|2. **VFIO Modules:** Ensure `vfio-pci` module is loaded before boot
|
||||
41|3. **PCIe Hotplug:** Disable for stability unless required
|
||||
42|4. **Memory Ballooning:** Disable in VM for consistent performance
|
||||
43|
|
||||
44|---
|
||||
45|
|
||||
46|*This guide is essential for GPU passthrough to VMs running LLM inference workloads.*
|
||||
47|
|
||||
@@ -1,56 +0,0 @@
|
||||
1|# 03 - AMD GPU Passthrough (Strix Halo) — Home
|
||||
2|**Purpose:** Detailed AMD APU passthrough configuration for host LLM access.
|
||||
3|
|
||||
4|## Overview
|
||||
5|
|
||||
6|This guide covers the complete setup for AMD Strix Halo GPU passthrough, enabling native LLM inference on AMD hardware.
|
||||
7|
|
||||
8|## What You'll Learn
|
||||
9|
|
||||
10|- **Hardware preparation:** Verify Strix Halo compatibility
|
||||
11|- **BIOS configuration:** Enable IOMMU and PCIe passthrough
|
||||
12|- **Kernel configuration:** Load VFIO modules properly
|
||||
13|- **Proxmox setup:** Configure GPU for VM passthrough
|
||||
14|- **Driver installation:** Vulkan, ROCm, HIP SDK integration
|
||||
15|- **Qwen3.5-MoE setup:** Configure for AMD GPU acceleration
|
||||
16|
|
||||
17|## Prerequisites
|
||||
18|
|
||||
19|- AMD Strix Halo APU with integrated Radeon graphics
|
||||
20|- Linux system kernel 5.4+ with IOMMU support
|
||||
21|- Proxmox VE 7.x or later
|
||||
22|- 16GB+ system RAM (8GB for APU graphics, 8GB for OS)
|
||||
23|- SSD storage for VM images
|
||||
24|
|
||||
25|## Quick Start
|
||||
26|
|
||||
27|```bash
|
||||
28|# Enable IOMMU in GRUB
|
||||
29|# Edit /etc/default/grub, add:
|
||||
30|# GRUB_CMDLINE_LINUX="amd_iommu=on iommu=pt"
|
||||
31|
|
||||
32|# Update GRUB
|
||||
33|update-grub
|
||||
34|
|
||||
35|# Load VFIO modules
|
||||
36|echo "vfio
|
||||
37|vfio_iommu_type1
|
||||
38|vfio_pci
|
||||
39|vfio_virqfd" | sudo tee /etc/modules-load.d/vfio.conf
|
||||
40|
|
||||
41|# Blacklist Radeon in VM
|
||||
42|modprobe -r radeon amdgpu
|
||||
43|
|
||||
44|# Reboot to apply changes
|
||||
45|reboot
|
||||
46|```
|
||||
47|
|
||||
48|## Related Guides
|
||||
49|
|
||||
50|- **[01 - Proxmox & VM Passthrough](../01\ -\ Proxmox\ \&\ VM\ Passthrough/)** — General passthrough setup
|
||||
51|- **[04 - Qwen3.5 Model Setup](../04\ -\ Qwen3.5\ Model\ Setup/)** — Model deployment
|
||||
52|
|
||||
53|---
|
||||
54|
|
||||
55|*Essential for running Qwen3.5-MoE locally on AMD hardware with Vulkan backend acceleration.*
|
||||
56|
|
||||
Reference in New Issue
Block a user