diff options
| author | Paul Buetow <paul@buetow.org> | 2026-05-24 13:09:29 +0300 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2026-05-24 13:09:29 +0300 |
| commit | bdab30227ef495d2fc4d841814f8f22f96ff9684 (patch) | |
| tree | 8014213435710318d3149de4fd40c3b1451e26b3 | |
| parent | 993b63cb32135bc8d45defd7d1549d83df200cad (diff) | |
docs: refresh README, hypr.fish, AGENTS.md for consolidated --vm CLI
| -rw-r--r-- | README.md | 25 | ||||
| -rw-r--r-- | hypr.fish | 8 |
2 files changed, 9 insertions, 24 deletions
@@ -175,10 +175,10 @@ abbr pi-hyperstack-gemma4 pi --model hyperstack2/cyankiwi/gemma-4-31B-it-AWQ-4b Then launch a session after the VM(s) are up: ```fish -pi-hyperstack # single-VM → GPT-OSS 120B on hyperstack.wg1 -pi-hyperstack-coder # two-VM → Qwen3-Coder-Next on VM1 -pi-hyperstack-qwen36 # two-VM → Qwen3.6 27B FP8 on VM2 -pi-hyperstack-gemma4 # two-VM → Gemma 4 31B on VM2 +pi-hyperstack # GPT-OSS 120B on VM1 +pi-hyperstack-coder # Qwen3-Coder-Next on VM1 +pi-hyperstack-qwen36 # Qwen3.6 27B FP8 on VM2 +pi-hyperstack-gemma4 # Gemma 4 31B on VM2 ``` ### Model configuration (`pi/agent/models.json`) @@ -256,7 +256,6 @@ No API key or account required. Uses DuckDuckGo's free HTML endpoint. | Config file | Default model | WireGuard IP | Hostname | |---|---|---|---| | `hyperstack-vm1.toml` | Qwen3-Coder-Next (AWQ-4bit) | `192.168.3.1` | `hyperstack1.wg1` | -| `hyperstack-vm1-nemotron.toml` | Nemotron-3-Super 120B (2× H100, TP=2, 1M ctx) | `192.168.3.1` | `hyperstack1.wg1` | | `hyperstack-vm2.toml` | Gemma 4 31B IT (AWQ-4bit) | `192.168.3.3` | `hyperstack2.wg1` | Each VM has independent state files so they can be managed separately: @@ -339,22 +338,6 @@ clear that trust file for intentional reprovisioning; unexpected host key change `hyperstack.rb` handles the full VM lifecycle automatically. All steps below (VM creation, WireGuard tunnel, vLLM Docker container) run in a single command. -### Single-VM setup - -```bash -# Deploy VM, configure WireGuard tunnel, pull and start vLLM (~10 min) -ruby hyperstack.rb create - -# Run end-to-end inference test over the tunnel -ruby hyperstack.rb test - -# Launch Pi coding agent connected to GPT-OSS 120B on the VM -pi-hyperstack # fish abbreviation from hyperstack.fish - -# Tear down the VM and remove WireGuard peer -ruby hyperstack.rb delete -``` - ### Two-VM setup ```bash @@ -1,6 +1,8 @@ # Dual-VM setup (hyperstack-vm1/vm2.toml -> hyperstack1/2.wg1) -abbr pi-hyperstack-coder pi --model hyperstack1/bullpoint/Qwen3-Coder-Next-AWQ-4bit -abbr pi-hyperstack-qwen36 pi --model hyperstack2/Qwen/Qwen3.6-27B-FP8 -abbr pi-hyperstack-gemma4 pi --model hyperstack2/cyankiwi/gemma-4-31B-it-AWQ-4bit +abbr pi-hyperstack-coder pi --model hyperstack1/bullpoint/Qwen3-Coder-Next-AWQ-4bit +abbr pi-hyperstack-qwen36 pi --model hyperstack2/Qwen/Qwen3.6-27B-FP8 +abbr pi-hyperstack-gemma4 pi --model hyperstack2/cyankiwi/gemma-4-31B-it-AWQ-4bit +abbr hyperstack-create ruby ~/git/hyperstack/hyperstack.rb create +abbr hyperstack-create-vm2 ruby ~/git/hyperstack/hyperstack.rb create --vm 2 abbr hyperstack-create-both ruby ~/git/hyperstack/hyperstack.rb create --vm both abbr hyperstack-delete-both ruby ~/git/hyperstack/hyperstack.rb delete --vm both |