jerome
b671546622
Created complete documentation structure with: • Root README.md with repository overview • Documentation directory structure (01-05 + templates) • Migrated content from public repository • New operational documentation • Comprehensive templates for business workflows Sections: 1. 01-business-strategy/ - Business vision, market analysis, financials 2. 02-technical-architecture/ - Infrastructure, AI agents, deployment 3. 03-operations/ - Client onboarding, support processes 4. 04-customer-portal/ - Placeholder for client-facing docs 5. 05-development/ - Placeholder for dev standards 6. templates/ - 5 reusable business templates This commit establishes the foundation for the repository reorganization. Content review will be conducted separately.
2.7 KiB
2.7 KiB
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|