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 hostname mapping: ana-ml2 = bare metal server at 10.250.50.54 (NOT VM 102). VM 102 = PFI-ANA_DOCKER at 10.250.50.70 (no longer associated with ana-ml2). Updates across Sites table, Host Reference, Docker Services header, Network Configuration, Scripts Reference targets, and Known Issue #6.

Browse Source
This commit is contained in:
Atlas
2026-04-10 18:49:39 -07:00
parent 5aecf76d8e
commit 28d3513ca7
1 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ATLAS/Infrastructure/Infrastructure-PFI-Project-Index.md
+11 -11
View File
@@ -24,7 +24,7 @@ keywords:
- inference-server - inference-server
- VM-102 - VM-102
links: [] links: []
modified: '2026-04-11T01:33:45+00:00' modified: '2026-04-11T01:49:39+00:00'
summary: Comprehensive architecture reference for the Infrastructure-PFI project covering summary: Comprehensive architecture reference for the Infrastructure-PFI project covering
three Tailscale-linked sites, 11 Proxmox VMs at PFI-ANA colo, 6 Docker services 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. with GPU workloads, and llama-swap model management across 20 models.
@@ -53,7 +53,7 @@ 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 | | **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-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 | Bare metal at 10.250.50.54 · VM 102 (10.250.50.70, ana-ml2) | FortiGate | | **PFI-ANA (Colo)** | 10.250.0.0/16 | Proxmox VE at 10.250.250.31:8006 | ana-ml2 (bare metal) at 10.250.50.54 · VM 102 (10.250.50.70) | FortiGate |
All sites are linked via Tailscale VPN (VM 106 at the colo). All sites are linked via Tailscale VPN (VM 106 at the colo).
@@ -61,7 +61,7 @@ All sites are linked via Tailscale VPN (VM 106 at the colo).
| Host | IP | Type | Role | | Host | IP | Type | Role |
|---|---|---|---| |---|---|---|---|
| **Bare Metal** | 10.250.50.54 | Physical server | Main inferencing server — direct GPU access, runs inference workloads | | **ana-ml2** (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 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 100** (PFI-ANA-TRUENAS) | — | Proxmox VM | NAS/iSCSI storage |
| **VM 101** (PFI-ANA-DC) | — | Proxmox VM | Windows Domain Controller | | **VM 101** (PFI-ANA-DC) | — | Proxmox VM | Windows Domain Controller |
@@ -119,7 +119,7 @@ Infrastructure-PFI/
│ ├── backup-chromadb.sh # Hot backup with 30-day retention │ ├── backup-chromadb.sh # Hot backup with 30-day retention
│ ├── health-check-chromadb.sh # Health monitoring with alerting │ ├── health-check-chromadb.sh # Health monitoring with alerting
│ ├── quickstart-chromadb.sh # One-command ChromaDB setup wrapper │ ├── quickstart-chromadb.sh # One-command ChromaDB setup wrapper
│ └── inference-hardware-profile.sh # Hardware profiler for AI/ML inference (bare metal 10.250.50.54) │ └── inference-hardware-profile.sh # Hardware profiler for AI/ML inference (ana-ml2 bare metal 10.250.50.54)
└── output/ # Generated output and logs (empty) └── output/ # Generated output and logs (empty)
``` ```
@@ -144,7 +144,7 @@ Ordered startup is configured to ensure dependencies are met before dependent se
--- ---
## Docker Services (VM 102: ana-ml2) ## Docker Services (VM 102: PFI-ANA_DOCKER)
Six services run on the Docker host, with most leveraging GPU acceleration for AI workloads. Six services run on the Docker host, with most leveraging GPU acceleration for AI workloads.
@@ -207,8 +207,8 @@ The llama-swap gateway manages **20 GGUF models** across multiple categories:
- Linux VMs: `virtio` - Linux VMs: `virtio`
- Windows VMs: `e1000` - Windows VMs: `e1000`
- **Docker Network**: Services on external network `traefik-net` - **Docker Network**: Services on external network `traefik-net`
- **Docker Host IP**: `10.250.50.70` (VM 102 / ana-ml2 / PFI-ANA_DOCKER) - **Docker Host IP**: `10.250.50.70` (VM 102 / PFI-ANA_DOCKER)
- **Bare Metal Inference Server IP**: `10.250.50.54` (physical server, direct GPU access) - **Bare Metal Inference Server IP**: ana-ml2 at `10.250.50.54` (physical server, direct GPU access)
--- ---
@@ -231,8 +231,8 @@ The llama-swap gateway manages **20 GGUF models** across multiple categories:
### inference-hardware-profile.sh ### inference-hardware-profile.sh
**Target Hosts:** **Target Hosts:**
- **Bare metal inferencing server** at `10.250.50.54` — primary target (direct GPU access) - **ana-ml2** (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) - **VM 102** (PFI-ANA_DOCKER) 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. 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.
@@ -255,7 +255,7 @@ A comprehensive system hardware profiler designed for AI/ML inference capacity p
| `--quick` | One-line summary | | `--quick` | One-line summary |
| `--gpu-only` | Full report without Docker sections | | `--gpu-only` | Full report without Docker sections |
> **⚠️ 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. > **⚠️ Action needed:** Run this script on **ana-ml2** (bare metal server at 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.
--- ---
@@ -266,7 +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 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 4. **Parakeet STT** references `.env` configuration not tracked in version control
5. **Qwen3-Coder-Next** download may be incomplete — `.incomplete` files present on disk 5. **Qwen3-Coder-Next** download may be incomplete — `.incomplete` files present on disk
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. 6. **Physical GPU model and VRAM undocumented** — the physical GPU(s) in the bare metal inferencing server ana-ml2 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 ana-ml2 and save the output to close this gap.
--- ---