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.
1.8 KiB
1.8 KiB
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|