vh/VuongKB
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update: ATLAS/Infrastructure/Infrastructure-PFI-Project-Index.md — Correct critical IP mapping error: 10.250.50.54 was incorrectly documented as VM 102 (Docker host). Correct mapping is 10.250.50.54 = bare metal inferencing server, 10.250.50.70 = VM 102 (PFI-ANA_DOCKER / ana-ml2). Added PFI-ANA Host Reference section. Updated all 6 affected sections: Sites table, File & Directory Map, Network Configuration, Scripts Reference, Known Issues, and new Host Reference table.

Browse Source
This commit is contained in:
Atlas
2026-04-10 18:33:45 -07:00
parent f45c5dcbd3
commit 5aecf76d8e
1 changed files with 32 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ATLAS/Infrastructure/Infrastructure-PFI-Project-Index.md
+32 -9
View File
@@ -16,9 +16,15 @@ keywords:
- gpu
- network
- llama-swap
- 'yes'
- bare-metal
- 10.250.50.54
- 10.250.50.70
- ana-ml2
- PFI-ANA_DOCKER
- inference-server
- VM-102
links: []
modified: '2026-04-11T01:28:16+00:00'
modified: '2026-04-11T01:33:45+00:00'
summary: Comprehensive architecture reference for the Infrastructure-PFI project covering
three Tailscale-linked sites, 11 Proxmox VMs at PFI-ANA colo, 6 Docker services
with GPU workloads, and llama-swap model management across 20 models.
@@ -29,6 +35,7 @@ tags:
- proxmox
- colocation
- reference
- hardware-audit
title: Infrastructure-PFI — Full Project Index & Architecture Reference
---
@@ -46,10 +53,23 @@ Infrastructure-PFI is the configuration and documentation project for the PFI ne
|---|---|---|---|---|
| **ESH-Home** | 10.0.0.0/16 | Proxmox VE | VM at 10.0.50.45 | Ubiquiti |
| **PFI-NH3** | 10.100.0.0/16 | Proxmox VE | Proxmox VM | Ubiquiti |
| **PFI-ANA (Colo)** | 10.250.0.0/16 | Proxmox VE at 10.250.250.31:8006 | VM 102 (10.250.50.54, ana-ml2) | FortiGate |
| **PFI-ANA (Colo)** | 10.250.0.0/16 | Proxmox VE at 10.250.250.31:8006 | Bare metal at 10.250.50.54 · VM 102 (10.250.50.70, ana-ml2) | FortiGate |
All sites are linked via Tailscale VPN (VM 106 at the colo).
### PFI-ANA Colo — Host Reference
| Host | IP | Type | Role |
|---|---|---|---|
| **Bare Metal** | 10.250.50.54 | Physical server | Main inferencing server — direct GPU access, runs inference workloads |
| **VM 102** (PFI-ANA_DOCKER) | 10.250.50.70 | Proxmox VM | Docker host — llama-swap, ComfyUI, VibeVoice, Parakeet, ChromaDB, Dockge |
| **VM 100** (PFI-ANA-TRUENAS) | — | Proxmox VM | NAS/iSCSI storage |
| **VM 101** (PFI-ANA-DC) | — | Proxmox VM | Windows Domain Controller |
| **VM 104** (PFI-Mongo) | 10.250.50.81 | Proxmox VM | MongoDB server |
| **VM 106** (PFI-Tailscale) | — | Proxmox VM | VPN gateway (Tailscale) |
The Proxmox hypervisor management interface is at `10.250.250.31:8006`.
---
## File & Directory Map
@@ -99,7 +119,7 @@ Infrastructure-PFI/
│ ├── backup-chromadb.sh # Hot backup with 30-day retention
│ ├── health-check-chromadb.sh # Health monitoring with alerting
│ ├── quickstart-chromadb.sh # One-command ChromaDB setup wrapper
│ └── inference-hardware-profile.sh # ⚠️ NEW — Hardware profiler for AI/ML inference planning (VM 102)
│ └── inference-hardware-profile.sh # Hardware profiler for AI/ML inference (bare metal 10.250.50.54)
└── output/ # Generated output and logs (empty)
```
@@ -187,7 +207,8 @@ The llama-swap gateway manages **20 GGUF models** across multiple categories:
- Linux VMs: `virtio`
- Windows VMs: `e1000`
- **Docker Network**: Services on external network `traefik-net`
- **Docker Host IP**: `10.250.50.54` (ana-ml2)
- **Docker Host IP**: `10.250.50.70` (VM 102 / ana-ml2 / PFI-ANA_DOCKER)
- **Bare Metal Inference Server IP**: `10.250.50.54` (physical server, direct GPU access)
---
@@ -205,11 +226,13 @@ The llama-swap gateway manages **20 GGUF models** across multiple categories:
| Script | Purpose |
|---|---|
| `nemotron-query.sh` | Bash client for querying Nemotron via llama-swap API |
| `inference-hardware-profile.sh` | **NEW** — Comprehensive hardware profiler for AI/ML inference planning |
| `inference-hardware-profile.sh` | Comprehensive hardware profiler for AI/ML inference planning |
### inference-hardware-profile.sh
**Target Host:** VM 102 (ana-ml2) at `10.250.50.54` — PFI-ANA Colo
**Target Hosts:**
- **Bare metal inferencing server** at `10.250.50.54` — primary target (direct GPU access)
- **VM 102 (PFI-ANA_DOCKER / ana-ml2)** at `10.250.50.70` — secondary target (GPU passthrough)
A comprehensive system hardware profiler designed for AI/ML inference capacity planning. Captures the full hardware picture needed to evaluate and optimize GPU inference workloads.
@@ -232,7 +255,7 @@ A comprehensive system hardware profiler designed for AI/ML inference capacity p
| `--quick` | One-line summary |
| `--gpu-only` | Full report without Docker sections |
> **⚠️ Action needed:** This script should be run on VM 102 to capture the **physical GPU model, VRAM capacity, and host hardware specs**, which are currently undocumented in this project. The output (especially `--json`) should be saved to close the hardware documentation gap.
> **⚠️ Action needed:** Run this script on the **bare metal server** (10.250.50.54) to capture the **physical GPU model, VRAM capacity, and host hardware specs**, which are currently undocumented. The output (especially `--json`) should be saved to close Known Issue #6. Optionally also run on VM 102 (10.250.50.70) for passthrough comparison.
---
@@ -243,7 +266,7 @@ A comprehensive system hardware profiler designed for AI/ML inference capacity p
3. **Granite 4 Small** has `ttl: 0` (persistent caching) but is not assigned to the utility group
4. **Parakeet STT** references `.env` configuration not tracked in version control
5. **Qwen3-Coder-Next** download may be incomplete — `.incomplete` files present on disk
6. **Physical GPU model and VRAM undocumented** — the physical GPU passed through to VM 102 (its model, total VRAM, PCIe slot, etc.) is not recorded anywhere in project documentation. Run `inference-hardware-profile.sh --json` on VM 102 and save the output to close this gap.
6. **Physical GPU model and VRAM undocumented** — the physical GPU(s) in the bare metal inferencing server at 10.250.50.54 (and those passed through to VM 102 at 10.250.50.70) are not recorded anywhere in project documentation. Run `inference-hardware-profile.sh --json` on the bare metal server and save the output to close this gap.
---