@draht/pods 2026.3.2-2

package/dist/scripts/pod_setup.sh

@@ -0,0 +1,336 @@
+#!/usr/bin/env bash
+# GPU pod bootstrap for vLLM deployment
+set -euo pipefail
+
+# Parse arguments passed from pi CLI
+MOUNT_COMMAND=""
+MODELS_PATH=""
+HF_TOKEN=""
+PI_API_KEY=""
+VLLM_VERSION="release"  # Default to release
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --mount)
+            MOUNT_COMMAND="$2"
+            shift 2
+            ;;
+        --models-path)
+            MODELS_PATH="$2"
+            shift 2
+            ;;
+        --hf-token)
+            HF_TOKEN="$2"
+            shift 2
+            ;;
+        --vllm-api-key)
+            PI_API_KEY="$2"
+            shift 2
+            ;;
+        --vllm)
+            VLLM_VERSION="$2"
+            shift 2
+            ;;
+        *)
+            echo "ERROR: Unknown option: $1" >&2
+            exit 1
+            ;;
+    esac
+done
+
+# Validate required parameters
+if [ -z "$HF_TOKEN" ]; then
+    echo "ERROR: HF_TOKEN is required" >&2
+    exit 1
+fi
+
+if [ -z "$PI_API_KEY" ]; then
+    echo "ERROR: PI_API_KEY is required" >&2
+    exit 1
+fi
+
+if [ -z "$MODELS_PATH" ]; then
+    echo "ERROR: MODELS_PATH is required" >&2
+    exit 1
+fi
+
+echo "=== Starting pod setup ==="
+
+# Install system dependencies
+apt update -y
+apt install -y python3-pip python3-venv git build-essential cmake ninja-build curl wget lsb-release htop pkg-config
+
+# --- Install matching CUDA toolkit -------------------------------------------
+echo "Checking CUDA driver version..."
+DRIVER_CUDA_VERSION=$(nvidia-smi | grep "CUDA Version" | awk '{print $9}')
+echo "Driver supports CUDA: $DRIVER_CUDA_VERSION"
+
+# Check if nvcc exists and its version
+if command -v nvcc &> /dev/null; then
+    NVCC_VERSION=$(nvcc --version | grep "release" | awk '{print $6}' | cut -d, -f1)
+    echo "Current nvcc version: $NVCC_VERSION"
+else
+    NVCC_VERSION="none"
+    echo "nvcc not found"
+fi
+
+# Install CUDA toolkit matching driver version if needed
+if [[ "$NVCC_VERSION" != "$DRIVER_CUDA_VERSION" ]]; then
+    echo "Installing CUDA Toolkit $DRIVER_CUDA_VERSION to match driver..."
+
+    # Detect Ubuntu version
+    UBUNTU_VERSION=$(lsb_release -rs)
+    UBUNTU_CODENAME=$(lsb_release -cs)
+
+    echo "Detected Ubuntu $UBUNTU_VERSION ($UBUNTU_CODENAME)"
+
+    # Map Ubuntu version to NVIDIA repo path
+    if [[ "$UBUNTU_VERSION" == "24.04" ]]; then
+        REPO_PATH="ubuntu2404"
+    elif [[ "$UBUNTU_VERSION" == "22.04" ]]; then
+        REPO_PATH="ubuntu2204"
+    elif [[ "$UBUNTU_VERSION" == "20.04" ]]; then
+        REPO_PATH="ubuntu2004"
+    else
+        echo "Warning: Unsupported Ubuntu version $UBUNTU_VERSION, trying ubuntu2204"
+        REPO_PATH="ubuntu2204"
+    fi
+
+    # Add NVIDIA package repositories
+    wget https://developer.download.nvidia.com/compute/cuda/repos/${REPO_PATH}/x86_64/cuda-keyring_1.1-1_all.deb
+    dpkg -i cuda-keyring_1.1-1_all.deb
+    rm cuda-keyring_1.1-1_all.deb
+    apt-get update
+
+    # Install specific CUDA toolkit version
+    # Convert version format (12.9 -> 12-9)
+    CUDA_VERSION_APT=$(echo $DRIVER_CUDA_VERSION | sed 's/\./-/')
+    echo "Installing cuda-toolkit-${CUDA_VERSION_APT}..."
+    apt-get install -y cuda-toolkit-${CUDA_VERSION_APT}
+
+    # Add CUDA to PATH
+    export PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/bin:$PATH
+    export LD_LIBRARY_PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/lib64:${LD_LIBRARY_PATH:-}
+
+    # Verify installation
+    nvcc --version
+else
+    echo "CUDA toolkit $NVCC_VERSION matches driver version"
+    export PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/bin:$PATH
+    export LD_LIBRARY_PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/lib64:${LD_LIBRARY_PATH:-}
+fi
+
+# --- Install uv (fast Python package manager) --------------------------------
+curl -LsSf https://astral.sh/uv/install.sh | sh
+export PATH="$HOME/.local/bin:$PATH"
+
+# --- Install Python 3.12 if not available ------------------------------------
+if ! command -v python3.12 &> /dev/null; then
+    echo "Python 3.12 not found. Installing via uv..."
+    uv python install 3.12
+fi
+
+# --- Clean up existing environments and caches -------------------------------
+echo "Cleaning up existing environments and caches..."
+
+# Remove existing venv for a clean installation
+VENV="$HOME/venv"
+if [ -d "$VENV" ]; then
+    echo "Removing existing virtual environment..."
+    rm -rf "$VENV"
+fi
+
+# Remove uv cache to ensure fresh installs
+if [ -d "$HOME/.cache/uv" ]; then
+    echo "Clearing uv cache..."
+    rm -rf "$HOME/.cache/uv"
+fi
+
+# Remove vLLM cache to avoid conflicts
+if [ -d "$HOME/.cache/vllm" ]; then
+    echo "Clearing vLLM cache..."
+    rm -rf "$HOME/.cache/vllm"
+fi
+
+# --- Create and activate venv ------------------------------------------------
+echo "Creating fresh virtual environment..."
+uv venv --python 3.12 --seed "$VENV"
+source "$VENV/bin/activate"
+
+# --- Install PyTorch and vLLM ------------------------------------------------
+echo "Installing vLLM and dependencies (version: $VLLM_VERSION)..."
+case "$VLLM_VERSION" in
+    release)
+        echo "Installing vLLM release with PyTorch..."
+        # Install vLLM with automatic PyTorch backend selection
+        # vLLM will automatically install the correct PyTorch version
+        uv pip install vllm>=0.10.0 --torch-backend=auto || {
+            echo "ERROR: Failed to install vLLM"
+            exit 1
+        }
+        ;;
+    nightly)
+        echo "Installing vLLM nightly with PyTorch..."
+        echo "This will install the latest nightly build of vLLM..."
+
+        # Install vLLM nightly with PyTorch
+        uv pip install -U vllm \
+            --torch-backend=auto \
+            --extra-index-url https://wheels.vllm.ai/nightly || {
+            echo "ERROR: Failed to install vLLM nightly"
+            exit 1
+        }
+
+        echo "vLLM nightly successfully installed!"
+        ;;
+    gpt-oss)
+        echo "Installing GPT-OSS special build with PyTorch nightly..."
+        echo "WARNING: This build is ONLY for GPT-OSS models!"
+        echo "Installing PyTorch nightly and cutting-edge dependencies..."
+
+        # Convert CUDA version format for PyTorch (12.4 -> cu124)
+        PYTORCH_CUDA="cu$(echo $DRIVER_CUDA_VERSION | sed 's/\.//')"
+        echo "Using PyTorch nightly with ${PYTORCH_CUDA} (driver supports ${DRIVER_CUDA_VERSION})"
+
+        # The GPT-OSS build will pull PyTorch nightly and other dependencies
+        # via the extra index URLs. We don't pre-install torch here to avoid conflicts.
+        uv pip install --pre vllm==0.10.1+gptoss \
+            --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
+            --extra-index-url https://download.pytorch.org/whl/nightly/${PYTORCH_CUDA} \
+            --index-strategy unsafe-best-match || {
+            echo "ERROR: Failed to install GPT-OSS vLLM build"
+            echo "This automatically installs PyTorch nightly with ${PYTORCH_CUDA}, Triton nightly, and other dependencies"
+            exit 1
+        }
+
+        # Install gpt-oss library for tool support
+        uv pip install gpt-oss || {
+            echo "WARNING: Failed to install gpt-oss library (needed for tool use)"
+        }
+        ;;
+    *)
+        echo "ERROR: Unknown vLLM version: $VLLM_VERSION"
+        exit 1
+        ;;
+esac
+
+# --- Install additional packages ---------------------------------------------
+echo "Installing additional packages..."
+# Note: tensorrt removed temporarily due to CUDA 13.0 compatibility issues
+# TensorRT still depends on deprecated nvidia-cuda-runtime-cu13 package
+uv pip install huggingface-hub psutil hf_transfer
+
+# --- FlashInfer installation (optional, improves performance) ----------------
+echo "Attempting FlashInfer installation (optional)..."
+if uv pip install flashinfer-python; then
+    echo "FlashInfer installed successfully"
+else
+    echo "FlashInfer not available, using Flash Attention instead"
+fi
+
+# --- Mount storage if provided -----------------------------------------------
+if [ -n "$MOUNT_COMMAND" ]; then
+    echo "Setting up mount..."
+
+    # Create mount point directory if it doesn't exist
+    mkdir -p "$MODELS_PATH"
+
+    # Execute the mount command
+    eval "$MOUNT_COMMAND" || {
+        echo "WARNING: Mount command failed, continuing without mount"
+    }
+
+    # Verify mount succeeded (optional, may not always be a mount point)
+    if mountpoint -q "$MODELS_PATH" 2>/dev/null; then
+        echo "Storage successfully mounted at $MODELS_PATH"
+    else
+        echo "Note: $MODELS_PATH is not a mount point (might be local storage)"
+    fi
+fi
+
+# --- Model storage setup ------------------------------------------------------
+echo ""
+echo "=== Setting up model storage ==="
+echo "Storage path: $MODELS_PATH"
+
+# Check if the path exists and is writable
+if [ ! -d "$MODELS_PATH" ]; then
+    echo "Creating model storage directory: $MODELS_PATH"
+    mkdir -p "$MODELS_PATH"
+fi
+
+if [ ! -w "$MODELS_PATH" ]; then
+    echo "ERROR: Model storage path is not writable: $MODELS_PATH"
+    echo "Please check permissions"
+    exit 1
+fi
+
+# Create the huggingface cache directory structure in the models path
+mkdir -p "${MODELS_PATH}/huggingface/hub"
+
+# Remove any existing cache directory or symlink
+if [ -e ~/.cache/huggingface ] || [ -L ~/.cache/huggingface ]; then
+    echo "Removing existing ~/.cache/huggingface..."
+    rm -rf ~/.cache/huggingface 2>/dev/null || true
+fi
+
+# Create parent directory if needed
+mkdir -p ~/.cache
+
+# Create symlink from ~/.cache/huggingface to the models path
+ln -s "${MODELS_PATH}/huggingface" ~/.cache/huggingface
+echo "Created symlink: ~/.cache/huggingface -> ${MODELS_PATH}/huggingface"
+
+# Verify the symlink works
+if [ -d ~/.cache/huggingface/hub ]; then
+    echo "✓ Model storage configured successfully"
+
+    # Check available space
+    AVAILABLE_SPACE=$(df -h "$MODELS_PATH" | awk 'NR==2 {print $4}')
+    echo "Available space: $AVAILABLE_SPACE"
+else
+    echo "ERROR: Could not verify model storage setup"
+    echo "The symlink was created but the target directory is not accessible"
+    exit 1
+fi
+
+# --- Configure environment ----------------------------------------------------
+mkdir -p ~/.config/vllm
+touch ~/.config/vllm/do_not_track
+
+# Write environment to .bashrc for persistence
+cat >> ~/.bashrc << EOF
+
+# Pi vLLM environment
+[ -d "\$HOME/venv" ] && source "\$HOME/venv/bin/activate"
+export PATH="/usr/local/cuda-${DRIVER_CUDA_VERSION}/bin:\$HOME/.local/bin:\$PATH"
+export LD_LIBRARY_PATH="/usr/local/cuda-${DRIVER_CUDA_VERSION}/lib64:\${LD_LIBRARY_PATH:-}"
+export HF_TOKEN="${HF_TOKEN}"
+export PI_API_KEY="${PI_API_KEY}"
+export HUGGING_FACE_HUB_TOKEN="${HF_TOKEN}"
+export HF_HUB_ENABLE_HF_TRANSFER=1
+export VLLM_NO_USAGE_STATS=1
+export VLLM_DO_NOT_TRACK=1
+export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
+EOF
+
+# Create log directory for vLLM
+mkdir -p ~/.vllm_logs
+
+# --- Output GPU info for pi CLI to parse -------------------------------------
+echo ""
+echo "===GPU_INFO_START==="
+nvidia-smi --query-gpu=index,name,memory.total --format=csv,noheader | while IFS=, read -r id name memory; do
+    # Trim whitespace
+    id=$(echo "$id" | xargs)
+    name=$(echo "$name" | xargs)
+    memory=$(echo "$memory" | xargs)
+    echo "{\"id\": $id, \"name\": \"$name\", \"memory\": \"$memory\"}"
+done
+echo "===GPU_INFO_END==="
+
+echo ""
+echo "=== Setup complete ==="
+echo "Pod is ready for vLLM deployments"
+echo "Models will be cached at: $MODELS_PATH"

package/dist/ssh.d.ts

@@ -0,0 +1,24 @@
+export interface SSHResult {
+    stdout: string;
+    stderr: string;
+    exitCode: number;
+}
+/**
+ * Execute an SSH command and return the result
+ */
+export declare const sshExec: (sshCmd: string, command: string, options?: {
+    keepAlive?: boolean | undefined;
+} | undefined) => Promise<SSHResult>;
+/**
+ * Execute an SSH command with streaming output to console
+ */
+export declare const sshExecStream: (sshCmd: string, command: string, options?: {
+    silent?: boolean | undefined;
+    forceTTY?: boolean | undefined;
+    keepAlive?: boolean | undefined;
+} | undefined) => Promise<number>;
+/**
+ * Copy a file to remote via SCP
+ */
+export declare const scpFile: (sshCmd: string, localPath: string, remotePath: string) => Promise<boolean>;
+//# sourceMappingURL=ssh.d.ts.map

package/dist/ssh.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"ssh.d.ts","sourceRoot":"","sources":["../src/ssh.ts"],"names":[],"mappings":"AAEA,MAAM,WAAW,SAAS;IACzB,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,QAAQ,EAAE,MAAM,CAAC;CACjB;AAED;;GAEG;AACH,eAAO,MAAM,OAAO;;oCAmDnB,CAAC;AAEF;;GAEG;AACH,eAAO,MAAM,aAAa;;;;iCAwCzB,CAAC;AAEF;;GAEG;AACH,eAAO,MAAM,OAAO,6EAsCnB,CAAC","sourcesContent":["import { type SpawnOptions, spawn } from \"child_process\";\n\nexport interface SSHResult {\n\tstdout: string;\n\tstderr: string;\n\texitCode: number;\n}\n\n/**\n * Execute an SSH command and return the result\n */\nexport const sshExec = async (\n\tsshCmd: string,\n\tcommand: string,\n\toptions?: { keepAlive?: boolean },\n): Promise<SSHResult> => {\n\treturn new Promise((resolve) => {\n\t\t// Parse SSH command (e.g., \"ssh root@1.2.3.4\" or \"ssh -p 22 root@1.2.3.4\")\n\t\tconst sshParts = sshCmd.split(\" \").filter((p) => p);\n\t\tconst sshBinary = sshParts[0];\n\t\tlet sshArgs = [...sshParts.slice(1)];\n\n\t\t// Add SSH keepalive options for long-running commands\n\t\tif (options?.keepAlive) {\n\t\t\t// ServerAliveInterval=30 sends keepalive every 30 seconds\n\t\t\t// ServerAliveCountMax=120 allows up to 120 failures (60 minutes total)\n\t\t\tsshArgs = [\"-o\", \"ServerAliveInterval=30\", \"-o\", \"ServerAliveCountMax=120\", ...sshArgs];\n\t\t}\n\n\t\tsshArgs.push(command);\n\n\t\tconst proc = spawn(sshBinary, sshArgs, {\n\t\t\tstdio: [\"ignore\", \"pipe\", \"pipe\"],\n\t\t});\n\n\t\tlet stdout = \"\";\n\t\tlet stderr = \"\";\n\n\t\tproc.stdout.on(\"data\", (data) => {\n\t\t\tstdout += data.toString();\n\t\t});\n\n\t\tproc.stderr.on(\"data\", (data) => {\n\t\t\tstderr += data.toString();\n\t\t});\n\n\t\tproc.on(\"close\", (code) => {\n\t\t\tresolve({\n\t\t\t\tstdout,\n\t\t\t\tstderr,\n\t\t\t\texitCode: code || 0,\n\t\t\t});\n\t\t});\n\n\t\tproc.on(\"error\", (err) => {\n\t\t\tresolve({\n\t\t\t\tstdout,\n\t\t\t\tstderr: err.message,\n\t\t\t\texitCode: 1,\n\t\t\t});\n\t\t});\n\t});\n};\n\n/**\n * Execute an SSH command with streaming output to console\n */\nexport const sshExecStream = async (\n\tsshCmd: string,\n\tcommand: string,\n\toptions?: { silent?: boolean; forceTTY?: boolean; keepAlive?: boolean },\n): Promise<number> => {\n\treturn new Promise((resolve) => {\n\t\tconst sshParts = sshCmd.split(\" \").filter((p) => p);\n\t\tconst sshBinary = sshParts[0];\n\n\t\t// Build SSH args\n\t\tlet sshArgs = [...sshParts.slice(1)];\n\n\t\t// Add -t flag if requested and not already present\n\t\tif (options?.forceTTY && !sshParts.includes(\"-t\")) {\n\t\t\tsshArgs = [\"-t\", ...sshArgs];\n\t\t}\n\n\t\t// Add SSH keepalive options for long-running commands\n\t\tif (options?.keepAlive) {\n\t\t\t// ServerAliveInterval=30 sends keepalive every 30 seconds\n\t\t\t// ServerAliveCountMax=120 allows up to 120 failures (60 minutes total)\n\t\t\tsshArgs = [\"-o\", \"ServerAliveInterval=30\", \"-o\", \"ServerAliveCountMax=120\", ...sshArgs];\n\t\t}\n\n\t\tsshArgs.push(command);\n\n\t\tconst spawnOptions: SpawnOptions = options?.silent\n\t\t\t? { stdio: [\"ignore\", \"ignore\", \"ignore\"] }\n\t\t\t: { stdio: \"inherit\" };\n\n\t\tconst proc = spawn(sshBinary, sshArgs, spawnOptions);\n\n\t\tproc.on(\"close\", (code) => {\n\t\t\tresolve(code || 0);\n\t\t});\n\n\t\tproc.on(\"error\", () => {\n\t\t\tresolve(1);\n\t\t});\n\t});\n};\n\n/**\n * Copy a file to remote via SCP\n */\nexport const scpFile = async (sshCmd: string, localPath: string, remotePath: string): Promise<boolean> => {\n\t// Extract host from SSH command\n\tconst sshParts = sshCmd.split(\" \").filter((p) => p);\n\tlet host = \"\";\n\tlet port = \"22\";\n\tlet i = 1; // Skip 'ssh'\n\n\twhile (i < sshParts.length) {\n\t\tif (sshParts[i] === \"-p\" && i + 1 < sshParts.length) {\n\t\t\tport = sshParts[i + 1];\n\t\t\ti += 2;\n\t\t} else if (!sshParts[i].startsWith(\"-\")) {\n\t\t\thost = sshParts[i];\n\t\t\tbreak;\n\t\t} else {\n\t\t\ti++;\n\t\t}\n\t}\n\n\tif (!host) {\n\t\tconsole.error(\"Could not parse host from SSH command\");\n\t\treturn false;\n\t}\n\n\t// Build SCP command\n\tconst scpArgs = [\"-P\", port, localPath, `${host}:${remotePath}`];\n\n\treturn new Promise((resolve) => {\n\t\tconst proc = spawn(\"scp\", scpArgs, { stdio: \"inherit\" });\n\n\t\tproc.on(\"close\", (code) => {\n\t\t\tresolve(code === 0);\n\t\t});\n\n\t\tproc.on(\"error\", () => {\n\t\t\tresolve(false);\n\t\t});\n\t});\n};\n"]}

package/dist/ssh.js

@@ -0,0 +1,115 @@
+import { spawn } from "child_process";
+/**
+ * Execute an SSH command and return the result
+ */
+export const sshExec = async (sshCmd, command, options) => {
+    return new Promise((resolve) => {
+        // Parse SSH command (e.g., "ssh root@1.2.3.4" or "ssh -p 22 root@1.2.3.4")
+        const sshParts = sshCmd.split(" ").filter((p) => p);
+        const sshBinary = sshParts[0];
+        let sshArgs = [...sshParts.slice(1)];
+        // Add SSH keepalive options for long-running commands
+        if (options?.keepAlive) {
+            // ServerAliveInterval=30 sends keepalive every 30 seconds
+            // ServerAliveCountMax=120 allows up to 120 failures (60 minutes total)
+            sshArgs = ["-o", "ServerAliveInterval=30", "-o", "ServerAliveCountMax=120", ...sshArgs];
+        }
+        sshArgs.push(command);
+        const proc = spawn(sshBinary, sshArgs, {
+            stdio: ["ignore", "pipe", "pipe"],
+        });
+        let stdout = "";
+        let stderr = "";
+        proc.stdout.on("data", (data) => {
+            stdout += data.toString();
+        });
+        proc.stderr.on("data", (data) => {
+            stderr += data.toString();
+        });
+        proc.on("close", (code) => {
+            resolve({
+                stdout,
+                stderr,
+                exitCode: code || 0,
+            });
+        });
+        proc.on("error", (err) => {
+            resolve({
+                stdout,
+                stderr: err.message,
+                exitCode: 1,
+            });
+        });
+    });
+};
+/**
+ * Execute an SSH command with streaming output to console
+ */
+export const sshExecStream = async (sshCmd, command, options) => {
+    return new Promise((resolve) => {
+        const sshParts = sshCmd.split(" ").filter((p) => p);
+        const sshBinary = sshParts[0];
+        // Build SSH args
+        let sshArgs = [...sshParts.slice(1)];
+        // Add -t flag if requested and not already present
+        if (options?.forceTTY && !sshParts.includes("-t")) {
+            sshArgs = ["-t", ...sshArgs];
+        }
+        // Add SSH keepalive options for long-running commands
+        if (options?.keepAlive) {
+            // ServerAliveInterval=30 sends keepalive every 30 seconds
+            // ServerAliveCountMax=120 allows up to 120 failures (60 minutes total)
+            sshArgs = ["-o", "ServerAliveInterval=30", "-o", "ServerAliveCountMax=120", ...sshArgs];
+        }
+        sshArgs.push(command);
+        const spawnOptions = options?.silent
+            ? { stdio: ["ignore", "ignore", "ignore"] }
+            : { stdio: "inherit" };
+        const proc = spawn(sshBinary, sshArgs, spawnOptions);
+        proc.on("close", (code) => {
+            resolve(code || 0);
+        });
+        proc.on("error", () => {
+            resolve(1);
+        });
+    });
+};
+/**
+ * Copy a file to remote via SCP
+ */
+export const scpFile = async (sshCmd, localPath, remotePath) => {
+    // Extract host from SSH command
+    const sshParts = sshCmd.split(" ").filter((p) => p);
+    let host = "";
+    let port = "22";
+    let i = 1; // Skip 'ssh'
+    while (i < sshParts.length) {
+        if (sshParts[i] === "-p" && i + 1 < sshParts.length) {
+            port = sshParts[i + 1];
+            i += 2;
+        }
+        else if (!sshParts[i].startsWith("-")) {
+            host = sshParts[i];
+            break;
+        }
+        else {
+            i++;
+        }
+    }
+    if (!host) {
+        console.error("Could not parse host from SSH command");
+        return false;
+    }
+    // Build SCP command
+    const scpArgs = ["-P", port, localPath, `${host}:${remotePath}`];
+    return new Promise((resolve) => {
+        const proc = spawn("scp", scpArgs, { stdio: "inherit" });
+        proc.on("close", (code) => {
+            resolve(code === 0);
+        });
+        proc.on("error", () => {
+            resolve(false);
+        });
+    });
+};
+//# sourceMappingURL=ssh.js.map

package/dist/ssh.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"ssh.js","sourceRoot":"","sources":["../src/ssh.ts"],"names":[],"mappings":"AAAA,OAAO,EAAqB,KAAK,EAAE,MAAM,eAAe,CAAC;AAQzD;;GAEG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,KAAK,EAC3B,MAAc,EACd,OAAe,EACf,OAAiC,EACZ,EAAE,CAAC;IACxB,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC;QAC/B,2EAA2E;QAC3E,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;QACpD,MAAM,SAAS,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAC;QAC9B,IAAI,OAAO,GAAG,CAAC,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;QAErC,sDAAsD;QACtD,IAAI,OAAO,EAAE,SAAS,EAAE,CAAC;YACxB,0DAA0D;YAC1D,uEAAuE;YACvE,OAAO,GAAG,CAAC,IAAI,EAAE,wBAAwB,EAAE,IAAI,EAAE,yBAAyB,EAAE,GAAG,OAAO,CAAC,CAAC;QACzF,CAAC;QAED,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QAEtB,MAAM,IAAI,GAAG,KAAK,CAAC,SAAS,EAAE,OAAO,EAAE;YACtC,KAAK,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC;SACjC,CAAC,CAAC;QAEH,IAAI,MAAM,GAAG,EAAE,CAAC;QAChB,IAAI,MAAM,GAAG,EAAE,CAAC;QAEhB,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC;YAChC,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;QAAA,CAC1B,CAAC,CAAC;QAEH,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC;YAChC,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;QAAA,CAC1B,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC;YAC1B,OAAO,CAAC;gBACP,MAAM;gBACN,MAAM;gBACN,QAAQ,EAAE,IAAI,IAAI,CAAC;aACnB,CAAC,CAAC;QAAA,CACH,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,EAAE,CAAC;YACzB,OAAO,CAAC;gBACP,MAAM;gBACN,MAAM,EAAE,GAAG,CAAC,OAAO;gBACnB,QAAQ,EAAE,CAAC;aACX,CAAC,CAAC;QAAA,CACH,CAAC,CAAC;IAAA,CACH,CAAC,CAAC;AAAA,CACH,CAAC;AAEF;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAG,KAAK,EACjC,MAAc,EACd,OAAe,EACf,OAAuE,EACrD,EAAE,CAAC;IACrB,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC;QAC/B,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;QACpD,MAAM,SAAS,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAC;QAE9B,iBAAiB;QACjB,IAAI,OAAO,GAAG,CAAC,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;QAErC,mDAAmD;QACnD,IAAI,OAAO,EAAE,QAAQ,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAC;YACnD,OAAO,GAAG,CAAC,IAAI,EAAE,GAAG,OAAO,CAAC,CAAC;QAC9B,CAAC;QAED,sDAAsD;QACtD,IAAI,OAAO,EAAE,SAAS,EAAE,CAAC;YACxB,0DAA0D;YAC1D,uEAAuE;YACvE,OAAO,GAAG,CAAC,IAAI,EAAE,wBAAwB,EAAE,IAAI,EAAE,yBAAyB,EAAE,GAAG,OAAO,CAAC,CAAC;QACzF,CAAC;QAED,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QAEtB,MAAM,YAAY,GAAiB,OAAO,EAAE,MAAM;YACjD,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,QAAQ,EAAE,QAAQ,EAAE,QAAQ,CAAC,EAAE;YAC3C,CAAC,CAAC,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC;QAExB,MAAM,IAAI,GAAG,KAAK,CAAC,SAAS,EAAE,OAAO,EAAE,YAAY,CAAC,CAAC;QAErD,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC;YAC1B,OAAO,CAAC,IAAI,IAAI,CAAC,CAAC,CAAC;QAAA,CACnB,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE,CAAC;YACtB,OAAO,CAAC,CAAC,CAAC,CAAC;QAAA,CACX,CAAC,CAAC;IAAA,CACH,CAAC,CAAC;AAAA,CACH,CAAC;AAEF;;GAEG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,KAAK,EAAE,MAAc,EAAE,SAAiB,EAAE,UAAkB,EAAoB,EAAE,CAAC;IACzG,gCAAgC;IAChC,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;IACpD,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,IAAI,IAAI,GAAG,IAAI,CAAC;IAChB,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,aAAa;IAExB,OAAO,CAAC,GAAG,QAAQ,CAAC,MAAM,EAAE,CAAC;QAC5B,IAAI,QAAQ,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,QAAQ,CAAC,MAAM,EAAE,CAAC;YACrD,IAAI,GAAG,QAAQ,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;YACvB,CAAC,IAAI,CAAC,CAAC;QACR,CAAC;aAAM,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YACzC,IAAI,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAC;YACnB,MAAM;QACP,CAAC;aAAM,CAAC;YACP,CAAC,EAAE,CAAC;QACL,CAAC;IACF,CAAC;IAED,IAAI,CAAC,IAAI,EAAE,CAAC;QACX,OAAO,CAAC,KAAK,CAAC,uCAAuC,CAAC,CAAC;QACvD,OAAO,KAAK,CAAC;IACd,CAAC;IAED,oBAAoB;IACpB,MAAM,OAAO,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE,GAAG,IAAI,IAAI,UAAU,EAAE,CAAC,CAAC;IAEjE,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC;QAC/B,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,EAAE,OAAO,EAAE,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;QAEzD,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC;YAC1B,OAAO,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC;QAAA,CACpB,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE,CAAC;YACtB,OAAO,CAAC,KAAK,CAAC,CAAC;QAAA,CACf,CAAC,CAAC;IAAA,CACH,CAAC,CAAC;AAAA,CACH,CAAC","sourcesContent":["import { type SpawnOptions, spawn } from \"child_process\";\n\nexport interface SSHResult {\n\tstdout: string;\n\tstderr: string;\n\texitCode: number;\n}\n\n/**\n * Execute an SSH command and return the result\n */\nexport const sshExec = async (\n\tsshCmd: string,\n\tcommand: string,\n\toptions?: { keepAlive?: boolean },\n): Promise<SSHResult> => {\n\treturn new Promise((resolve) => {\n\t\t// Parse SSH command (e.g., \"ssh root@1.2.3.4\" or \"ssh -p 22 root@1.2.3.4\")\n\t\tconst sshParts = sshCmd.split(\" \").filter((p) => p);\n\t\tconst sshBinary = sshParts[0];\n\t\tlet sshArgs = [...sshParts.slice(1)];\n\n\t\t// Add SSH keepalive options for long-running commands\n\t\tif (options?.keepAlive) {\n\t\t\t// ServerAliveInterval=30 sends keepalive every 30 seconds\n\t\t\t// ServerAliveCountMax=120 allows up to 120 failures (60 minutes total)\n\t\t\tsshArgs = [\"-o\", \"ServerAliveInterval=30\", \"-o\", \"ServerAliveCountMax=120\", ...sshArgs];\n\t\t}\n\n\t\tsshArgs.push(command);\n\n\t\tconst proc = spawn(sshBinary, sshArgs, {\n\t\t\tstdio: [\"ignore\", \"pipe\", \"pipe\"],\n\t\t});\n\n\t\tlet stdout = \"\";\n\t\tlet stderr = \"\";\n\n\t\tproc.stdout.on(\"data\", (data) => {\n\t\t\tstdout += data.toString();\n\t\t});\n\n\t\tproc.stderr.on(\"data\", (data) => {\n\t\t\tstderr += data.toString();\n\t\t});\n\n\t\tproc.on(\"close\", (code) => {\n\t\t\tresolve({\n\t\t\t\tstdout,\n\t\t\t\tstderr,\n\t\t\t\texitCode: code || 0,\n\t\t\t});\n\t\t});\n\n\t\tproc.on(\"error\", (err) => {\n\t\t\tresolve({\n\t\t\t\tstdout,\n\t\t\t\tstderr: err.message,\n\t\t\t\texitCode: 1,\n\t\t\t});\n\t\t});\n\t});\n};\n\n/**\n * Execute an SSH command with streaming output to console\n */\nexport const sshExecStream = async (\n\tsshCmd: string,\n\tcommand: string,\n\toptions?: { silent?: boolean; forceTTY?: boolean; keepAlive?: boolean },\n): Promise<number> => {\n\treturn new Promise((resolve) => {\n\t\tconst sshParts = sshCmd.split(\" \").filter((p) => p);\n\t\tconst sshBinary = sshParts[0];\n\n\t\t// Build SSH args\n\t\tlet sshArgs = [...sshParts.slice(1)];\n\n\t\t// Add -t flag if requested and not already present\n\t\tif (options?.forceTTY && !sshParts.includes(\"-t\")) {\n\t\t\tsshArgs = [\"-t\", ...sshArgs];\n\t\t}\n\n\t\t// Add SSH keepalive options for long-running commands\n\t\tif (options?.keepAlive) {\n\t\t\t// ServerAliveInterval=30 sends keepalive every 30 seconds\n\t\t\t// ServerAliveCountMax=120 allows up to 120 failures (60 minutes total)\n\t\t\tsshArgs = [\"-o\", \"ServerAliveInterval=30\", \"-o\", \"ServerAliveCountMax=120\", ...sshArgs];\n\t\t}\n\n\t\tsshArgs.push(command);\n\n\t\tconst spawnOptions: SpawnOptions = options?.silent\n\t\t\t? { stdio: [\"ignore\", \"ignore\", \"ignore\"] }\n\t\t\t: { stdio: \"inherit\" };\n\n\t\tconst proc = spawn(sshBinary, sshArgs, spawnOptions);\n\n\t\tproc.on(\"close\", (code) => {\n\t\t\tresolve(code || 0);\n\t\t});\n\n\t\tproc.on(\"error\", () => {\n\t\t\tresolve(1);\n\t\t});\n\t});\n};\n\n/**\n * Copy a file to remote via SCP\n */\nexport const scpFile = async (sshCmd: string, localPath: string, remotePath: string): Promise<boolean> => {\n\t// Extract host from SSH command\n\tconst sshParts = sshCmd.split(\" \").filter((p) => p);\n\tlet host = \"\";\n\tlet port = \"22\";\n\tlet i = 1; // Skip 'ssh'\n\n\twhile (i < sshParts.length) {\n\t\tif (sshParts[i] === \"-p\" && i + 1 < sshParts.length) {\n\t\t\tport = sshParts[i + 1];\n\t\t\ti += 2;\n\t\t} else if (!sshParts[i].startsWith(\"-\")) {\n\t\t\thost = sshParts[i];\n\t\t\tbreak;\n\t\t} else {\n\t\t\ti++;\n\t\t}\n\t}\n\n\tif (!host) {\n\t\tconsole.error(\"Could not parse host from SSH command\");\n\t\treturn false;\n\t}\n\n\t// Build SCP command\n\tconst scpArgs = [\"-P\", port, localPath, `${host}:${remotePath}`];\n\n\treturn new Promise((resolve) => {\n\t\tconst proc = spawn(\"scp\", scpArgs, { stdio: \"inherit\" });\n\n\t\tproc.on(\"close\", (code) => {\n\t\t\tresolve(code === 0);\n\t\t});\n\n\t\tproc.on(\"error\", () => {\n\t\t\tresolve(false);\n\t\t});\n\t});\n};\n"]}

package/dist/types.d.ts

@@ -0,0 +1,23 @@
+export interface GPU {
+    id: number;
+    name: string;
+    memory: string;
+}
+export interface Model {
+    model: string;
+    port: number;
+    gpu: number[];
+    pid: number;
+}
+export interface Pod {
+    ssh: string;
+    gpus: GPU[];
+    models: Record<string, Model>;
+    modelsPath?: string;
+    vllmVersion?: "release" | "nightly" | "gpt-oss";
+}
+export interface Config {
+    pods: Record<string, Pod>;
+    active?: string;
+}
+//# sourceMappingURL=types.d.ts.map

package/dist/types.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAEA,MAAM,WAAW,GAAG;IACnB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,MAAM,CAAC;CACf;AAED,MAAM,WAAW,KAAK;IACrB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;IACb,GAAG,EAAE,MAAM,EAAE,CAAC;IACd,GAAG,EAAE,MAAM,CAAC;CACZ;AAED,MAAM,WAAW,GAAG;IACnB,GAAG,EAAE,MAAM,CAAC;IACZ,IAAI,EAAE,GAAG,EAAE,CAAC;IACZ,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;IAC9B,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,WAAW,CAAC,EAAE,SAAS,GAAG,SAAS,GAAG,SAAS,CAAC;CAChD;AAED,MAAM,WAAW,MAAM;IACtB,IAAI,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC;IAC1B,MAAM,CAAC,EAAE,MAAM,CAAC;CAChB","sourcesContent":["// Core type definitions for pi\n\nexport interface GPU {\n\tid: number;\n\tname: string;\n\tmemory: string;\n}\n\nexport interface Model {\n\tmodel: string;\n\tport: number;\n\tgpu: number[]; // Array of GPU IDs for multi-GPU deployment\n\tpid: number;\n}\n\nexport interface Pod {\n\tssh: string;\n\tgpus: GPU[];\n\tmodels: Record<string, Model>;\n\tmodelsPath?: string;\n\tvllmVersion?: \"release\" | \"nightly\" | \"gpt-oss\"; // Track which vLLM version is installed\n}\n\nexport interface Config {\n\tpods: Record<string, Pod>;\n\tactive?: string;\n}\n"]}

package/dist/types.js

@@ -0,0 +1,3 @@
+// Core type definitions for pi
+export {};
+//# sourceMappingURL=types.js.map

package/dist/types.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"types.js","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAAA,+BAA+B","sourcesContent":["// Core type definitions for pi\n\nexport interface GPU {\n\tid: number;\n\tname: string;\n\tmemory: string;\n}\n\nexport interface Model {\n\tmodel: string;\n\tport: number;\n\tgpu: number[]; // Array of GPU IDs for multi-GPU deployment\n\tpid: number;\n}\n\nexport interface Pod {\n\tssh: string;\n\tgpus: GPU[];\n\tmodels: Record<string, Model>;\n\tmodelsPath?: string;\n\tvllmVersion?: \"release\" | \"nightly\" | \"gpt-oss\"; // Track which vLLM version is installed\n}\n\nexport interface Config {\n\tpods: Record<string, Pod>;\n\tactive?: string;\n}\n"]}

package/package.json

@@ -0,0 +1,40 @@
+{
+	"name": "@draht/pods",
+	"version": "2026.3.2-2",
+	"description": "CLI tool for managing vLLM deployments on GPU pods",
+	"type": "module",
+	"bin": {
+		"draht-pods": "dist/cli.js"
+	},
+	"scripts": {
+		"clean": "rm -rf dist",
+		"build": "tsgo -p tsconfig.build.json && cp src/models.json dist/ && cp -r scripts dist/",
+		"prepublishOnly": "bun run clean && bun run build"
+	},
+	"files": [
+		"dist",
+		"scripts"
+	],
+	"keywords": [
+		"llm",
+		"vllm",
+		"gpu",
+		"ai",
+		"cli"
+	],
+	"author": "Mario Zechner",
+	"license": "MIT",
+	"repository": {
+		"type": "git",
+		"url": "git+https://github.com/badlogic/pi-mono.git",
+		"directory": "packages/pods"
+	},
+	"engines": {
+		"node": ">=20.0.0"
+	},
+	"dependencies": {
+		"@draht/agent-core": "2026.3.1-7",
+		"chalk": "^5.5.0"
+	},
+	"devDependencies": {}
+}

package/scripts/model_run.sh

@@ -0,0 +1,83 @@
+#!/usr/bin/env bash
+# Model runner script - runs sequentially, killed by pi stop
+set -euo pipefail
+
+# These values are replaced before upload by pi CLI
+MODEL_ID="{{MODEL_ID}}"
+NAME="{{NAME}}"
+PORT="{{PORT}}"
+VLLM_ARGS="{{VLLM_ARGS}}"
+
+# Trap to ensure cleanup on exit and kill any child processes
+cleanup() {
+    local exit_code=$?
+    echo "Model runner exiting with code $exit_code"
+    # Kill any child processes
+    pkill -P $$ 2>/dev/null || true
+    exit $exit_code
+}
+trap cleanup EXIT TERM INT
+
+# Force colored output even when not a TTY
+export FORCE_COLOR=1
+export PYTHONUNBUFFERED=1
+export TERM=xterm-256color
+export RICH_FORCE_TERMINAL=1
+export CLICOLOR_FORCE=1
+
+# Source virtual environment
+source /root/venv/bin/activate
+
+echo "========================================="
+echo "Model Run: $NAME"
+echo "Model ID: $MODEL_ID"
+echo "Port: $PORT"
+if [ -n "$VLLM_ARGS" ]; then
+    echo "vLLM Args: $VLLM_ARGS"
+fi
+echo "========================================="
+echo ""
+
+# Download model (with color progress bars)
+echo "Downloading model (will skip if cached)..."
+HF_HUB_ENABLE_HF_TRANSFER=1 hf download "$MODEL_ID"
+
+if [ $? -ne 0 ]; then
+    echo "❌ ERROR: Failed to download model" >&2
+    exit 1
+fi
+
+echo ""
+echo "✅ Model download complete"
+echo ""
+
+# Build vLLM command
+VLLM_CMD="vllm serve '$MODEL_ID' --port $PORT --api-key '$PI_API_KEY'"
+if [ -n "$VLLM_ARGS" ]; then
+    VLLM_CMD="$VLLM_CMD $VLLM_ARGS"
+fi
+
+echo "Starting vLLM server..."
+echo "Command: $VLLM_CMD"
+echo "========================================="
+echo ""
+
+# Run vLLM in background so we can monitor it
+echo "Starting vLLM process..."
+bash -c "$VLLM_CMD" &
+VLLM_PID=$!
+
+# Monitor the vLLM process
+echo "Monitoring vLLM process (PID: $VLLM_PID)..."
+wait $VLLM_PID
+VLLM_EXIT_CODE=$?
+
+if [ $VLLM_EXIT_CODE -ne 0 ]; then
+    echo "❌ ERROR: vLLM exited with code $VLLM_EXIT_CODE" >&2
+    # Make sure to exit the script command too
+    kill -TERM $$ 2>/dev/null || true
+    exit $VLLM_EXIT_CODE
+fi
+
+echo "✅ vLLM exited normally"
+exit 0