@mariozechner/pi-pods

npm install -g @mariozechner/pi-pods

# Set required environment variables
export HF_TOKEN=your_huggingface_token      # Get from https://huggingface.co/settings/tokens
export PI_API_KEY=your_api_key              # Any string you want for API authentication

# Setup a DataCrunch pod with NFS storage
pi-pods setup dc1 "ssh [email protected]" \
  --mount "sudo mount -t nfs -o nconnect=16 nfs.fin-02.datacrunch.io:/your-pseudo /mnt/hf-models"

# Start a model (automatic configuration for known models)
pi start Qwen/Qwen2.5-Coder-32B-Instruct --name qwen

# Send a single message to the model
pi agent qwen "What is the Fibonacci sequence?"

# Interactive chat mode with file system tools
pi agent qwen -i

# Use with any OpenAI-compatible client
export OPENAI_BASE_URL='http://1.2.3.4:8001/v1'
export OPENAI_API_KEY=$PI_API_KEY

pi-pods setup <name> "<ssh>" [options]        # Setup new pod
  --mount "<mount_command>"                   # Run mount command during setup
  --models-path <path>                        # Override extracted path (optional)
  --vllm release|nightly|gpt-oss              # vLLM version (default: release)

pi-pods                                       # List all configured pods
pi-pods active <name>                         # Switch active pod
pi-pods remove <name>                         # Remove pod from local config
pi shell [<name>]                             # SSH into pod
pi ssh [<name>] "<command>"                   # Run command on pod

pi start <model> --name <name> [options]  # Start a model
  --memory <percent>      # GPU memory: 30%, 50%, 90% (default: 90%)
  --context <size>        # Context window: 4k, 8k, 16k, 32k, 64k, 128k
  --gpus <count>          # Number of GPUs to use (predefined models only)
  --pod <name>            # Target specific pod (overrides active)
  --vllm <args...>        # Pass custom args directly to vLLM

pi stop [<name>]          # Stop model (or all if no name given)
pi list                   # List running models with status
pi logs <name>            # Stream model logs (tail -f)

pi agent <name> "<message>"               # Single message to model
pi agent <name> "<msg1>" "<msg2>"         # Multiple messages in sequence
pi agent <name> -i                        # Interactive chat mode
pi agent <name> -i -c                     # Continue previous session

# Standalone OpenAI-compatible agent (works with any API)
pi-agent --base-url http://localhost:8000/v1 --model llama-3.1 "Hello"
pi-agent --api-key sk-... "What is 2+2?"  # Uses OpenAI by default
pi-agent --json "What is 2+2?"            # Output event stream as JSONL
pi-agent -i                                # Interactive mode

# Qwen2.5-Coder-32B - Excellent coding model, fits on single H100/H200
pi start Qwen/Qwen2.5-Coder-32B-Instruct --name qwen

# Qwen3-Coder-30B - Advanced reasoning with tool use
pi start Qwen/Qwen3-Coder-30B-A3B-Instruct --name qwen3

# Qwen3-Coder-480B - State-of-the-art on 8xH200 (data-parallel mode)
pi start Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 --name qwen-480b

# Requires special vLLM build during setup
pi-pods setup gpt-pod "ssh [email protected]" --models-path /workspace --vllm gpt-oss

# GPT-OSS-20B - Fits on 16GB+ VRAM
pi start openai/gpt-oss-20b --name gpt20

# GPT-OSS-120B - Needs 60GB+ VRAM
pi start openai/gpt-oss-120b --name gpt120

# GLM-4.5 - Requires 8-16 GPUs, includes thinking mode
pi start zai-org/GLM-4.5 --name glm

# GLM-4.5-Air - Smaller version, 1-2 GPUs
pi start zai-org/GLM-4.5-Air --name glm-air

# DeepSeek with custom settings
pi start deepseek-ai/DeepSeek-V3 --name deepseek --vllm \
  --tensor-parallel-size 4 --trust-remote-code

# Mistral with pipeline parallelism
pi start mistralai/Mixtral-8x22B-Instruct-v0.1 --name mixtral --vllm \
  --tensor-parallel-size 8 --pipeline-parallel-size 2

# Any model with specific tool parser
pi start some/model --name mymodel --vllm \
  --tool-call-parser hermes --enable-auto-tool-choice

pi start model1 --name m1  # Auto-assigns to GPU 0
pi start model2 --name m2  # Auto-assigns to GPU 1
pi start model3 --name m3  # Auto-assigns to GPU 2

# Run Qwen on 1 GPU instead of all available
pi start Qwen/Qwen2.5-Coder-32B-Instruct --name qwen --gpus 1

# Run GLM-4.5 on 8 GPUs (if it has an 8-GPU config)
pi start zai-org/GLM-4.5 --name glm --gpus 8

# Use all available GPUs
pi start meta-llama/Llama-3.1-70B-Instruct --name llama70b --vllm \
  --tensor-parallel-size 4

# Specific GPU count
pi start Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 --name qwen480 --vllm \
  --data-parallel-size 8 --enable-expert-parallel

from openai import OpenAI

client = OpenAI(
    base_url="http://your-pod-ip:8001/v1",
    api_key="your-pi-api-key"
)

# Chat completion with tool calling
response = client.chat.completions.create(
    model="Qwen/Qwen2.5-Coder-32B-Instruct",
    messages=[
        {"role": "user", "content": "Write a Python function to calculate fibonacci"}
    ],
    tools=[{
        "type": "function",
        "function": {
            "name": "execute_code",
            "description": "Execute Python code",
            "parameters": {
                "type": "object",
                "properties": {
                    "code": {"type": "string"}
                },
                "required": ["code"]
            }
        }
    }],
    tool_choice="auto"
)

pi start model --name mymodel --vllm --disable-tool-call-parser

# Large context for code analysis, moderate concurrency
pi start Qwen/Qwen2.5-Coder-32B-Instruct --name coder \
  --context 64k --memory 70%

# Start new session
pi agent qwen -i

# Continue previous session (maintains chat history)
pi agent qwen -i -c

# Check GPU usage
pi ssh "nvidia-smi"

# Check if port is in use
pi list

# Force stop all models
pi stop