@mariozechner/pi 0.1.5 → 0.5.0

package/dist/models.json

@@ -0,0 +1,305 @@
+{
+	"models": {
+		"Qwen/Qwen2.5-Coder-32B-Instruct": {
+			"name": "Qwen2.5-Coder-32B",
+			"configs": [
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--tool-call-parser", "hermes", "--enable-auto-tool-choice"]
+				},
+				{
+					"gpuCount": 2,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--tensor-parallel-size", "2", "--tool-call-parser", "hermes", "--enable-auto-tool-choice"]
+				}
+			]
+		},
+		"Qwen/Qwen3-Coder-30B-A3B-Instruct": {
+			"name": "Qwen3-Coder-30B",
+			"configs": [
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--enable-auto-tool-choice", "--tool-call-parser", "qwen3_coder"],
+					"notes": "Fits comfortably on single GPU. ~60GB model weight."
+				},
+				{
+					"gpuCount": 2,
+					"gpuTypes": ["H100", "H200"],
+					"args": [
+						"--tensor-parallel-size",
+						"2",
+						"--enable-auto-tool-choice",
+						"--tool-call-parser",
+						"qwen3_coder"
+					],
+					"notes": "For higher throughput/longer context."
+				}
+			]
+		},
+		"Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8": {
+			"name": "Qwen3-Coder-30B-FP8",
+			"configs": [
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--enable-auto-tool-choice", "--tool-call-parser", "qwen3_coder"],
+					"env": {
+						"VLLM_USE_DEEP_GEMM": "1"
+					},
+					"notes": "FP8 quantized, ~30GB model weight. Excellent for single GPU deployment."
+				}
+			]
+		},
+		"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
+			"name": "Qwen3-Coder-480B",
+			"configs": [
+				{
+					"gpuCount": 8,
+					"gpuTypes": ["H200", "H20"],
+					"args": [
+						"--tensor-parallel-size",
+						"8",
+						"--max-model-len",
+						"32000",
+						"--enable-auto-tool-choice",
+						"--tool-call-parser",
+						"qwen3_coder"
+					],
+					"notes": "Cannot serve full 262K context on single node. Reduce max-model-len or increase gpu-memory-utilization."
+				}
+			]
+		},
+		"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
+			"name": "Qwen3-Coder-480B-FP8",
+			"configs": [
+				{
+					"gpuCount": 8,
+					"gpuTypes": ["H200", "H20"],
+					"args": [
+						"--max-model-len",
+						"131072",
+						"--enable-expert-parallel",
+						"--data-parallel-size",
+						"8",
+						"--enable-auto-tool-choice",
+						"--tool-call-parser",
+						"qwen3_coder"
+					],
+					"env": {
+						"VLLM_USE_DEEP_GEMM": "1"
+					},
+					"notes": "Use data-parallel mode (not tensor-parallel) to avoid weight quantization errors."
+				}
+			]
+		},
+		"openai/gpt-oss-20b": {
+			"name": "GPT-OSS-20B",
+			"configs": [
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--async-scheduling"]
+				},
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["B200"],
+					"args": ["--async-scheduling"],
+					"env": {
+						"VLLM_USE_TRTLLM_ATTENTION": "1",
+						"VLLM_USE_TRTLLM_DECODE_ATTENTION": "1",
+						"VLLM_USE_TRTLLM_CONTEXT_ATTENTION": "1",
+						"VLLM_USE_FLASHINFER_MXFP4_MOE": "1"
+					}
+				}
+			],
+			"notes": "Requires vLLM 0.10.1+gptoss. Tools/functoin calls only  via /v1/responses endpoint."
+		},
+		"openai/gpt-oss-120b": {
+			"name": "GPT-OSS-120B",
+			"configs": [
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--async-scheduling", "--gpu-memory-utilization", "0.95", "--max-num-batched-tokens", "1024"],
+					"notes": "Single GPU deployment. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
+				},
+				{
+					"gpuCount": 2,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--tensor-parallel-size", "2", "--async-scheduling", "--gpu-memory-utilization", "0.94"],
+					"notes": "Recommended for H100/H200. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
+				},
+				{
+					"gpuCount": 4,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--tensor-parallel-size", "4", "--async-scheduling"],
+					"notes": "Higher throughput. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
+				},
+				{
+					"gpuCount": 8,
+					"gpuTypes": ["H100", "H200"],
+					"args": ["--tensor-parallel-size", "8", "--async-scheduling"],
+					"notes": "Maximum throughput for evaluation workloads. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
+				}
+			]
+		},
+		"zai-org/GLM-4.5": {
+			"name": "GLM-4.5",
+			"configs": [
+				{
+					"gpuCount": 16,
+					"gpuTypes": ["H100"],
+					"args": [
+						"--tensor-parallel-size",
+						"16",
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice"
+					]
+				},
+				{
+					"gpuCount": 8,
+					"gpuTypes": ["H200"],
+					"args": [
+						"--tensor-parallel-size",
+						"8",
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice"
+					]
+				}
+			],
+			"notes": "Models default to thinking mode. For full 128K context, double the GPU count."
+		},
+		"zai-org/GLM-4.5-FP8": {
+			"name": "GLM-4.5-FP8",
+			"configs": [
+				{
+					"gpuCount": 8,
+					"gpuTypes": ["H100"],
+					"args": [
+						"--tensor-parallel-size",
+						"8",
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice"
+					]
+				},
+				{
+					"gpuCount": 4,
+					"gpuTypes": ["H200"],
+					"args": [
+						"--tensor-parallel-size",
+						"4",
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice"
+					]
+				}
+			]
+		},
+		"zai-org/GLM-4.5-Air-FP8": {
+			"name": "GLM-4.5-Air-FP8",
+			"configs": [
+				{
+					"gpuCount": 2,
+					"gpuTypes": ["H100"],
+					"args": [
+						"--tensor-parallel-size",
+						"2",
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice",
+						"--quantization",
+						"fp8"
+					],
+					"env": {
+						"VLLM_ATTENTION_BACKEND": "XFORMERS"
+					},
+					"notes": "FP8 model requires vLLM with proper FP8 support or MTP module"
+				},
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["H200"],
+					"args": [
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice",
+						"--quantization",
+						"fp8"
+					],
+					"env": {
+						"VLLM_ATTENTION_BACKEND": "XFORMERS"
+					},
+					"notes": "FP8 model requires vLLM with proper FP8 support or MTP module"
+				}
+			]
+		},
+		"zai-org/GLM-4.5-Air": {
+			"name": "GLM-4.5-Air",
+			"configs": [
+				{
+					"gpuCount": 2,
+					"gpuTypes": ["H100", "H200"],
+					"args": [
+						"--tensor-parallel-size",
+						"2",
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice"
+					],
+					"notes": "Non-quantized BF16 version, more compatible"
+				},
+				{
+					"gpuCount": 1,
+					"gpuTypes": ["H200"],
+					"args": [
+						"--tool-call-parser",
+						"glm4_moe",
+						"--reasoning-parser",
+						"glm4_moe",
+						"--enable-auto-tool-choice",
+						"--gpu-memory-utilization",
+						"0.95"
+					],
+					"notes": "Single H200 can fit the BF16 model with high memory utilization"
+				}
+			]
+		},
+		"moonshotai/Kimi-K2-Instruct": {
+			"name": "Kimi-K2",
+			"configs": [
+				{
+					"gpuCount": 16,
+					"gpuTypes": ["H200", "H20"],
+					"args": [
+						"--tensor-parallel-size",
+						"16",
+						"--trust-remote-code",
+						"--enable-auto-tool-choice",
+						"--tool-call-parser",
+						"kimi_k2"
+					],
+					"notes": "Pure TP mode. For >16 GPUs, combine with pipeline-parallelism."
+				}
+			],
+			"notes": "Requires vLLM v0.10.0rc1+. Minimum 16 GPUs for FP8 with 128k context."
+		}
+	}
+}

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;
+}) => Promise<SSHResult>;
+/**
+ * Execute an SSH command with streaming output to console
+ */
+export declare const sshExecStream: (sshCmd: string, command: string, options?: {
+    silent?: boolean;
+    forceTTY?: boolean;
+    keepAlive?: boolean;
+}) => 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,GACnB,QAAQ,MAAM,EACd,SAAS,MAAM,EACf,UAAU;IAAE,SAAS,CAAC,EAAE,OAAO,CAAA;CAAE,KAC/B,OAAO,CAAC,SAAS,CA+CnB,CAAC;AAEF;;GAEG;AACH,eAAO,MAAM,aAAa,GACzB,QAAQ,MAAM,EACd,SAAS,MAAM,EACf,UAAU;IAAE,MAAM,CAAC,EAAE,OAAO,CAAC;IAAC,QAAQ,CAAC,EAAE,OAAO,CAAC;IAAC,SAAS,CAAC,EAAE,OAAO,CAAA;CAAE,KACrE,OAAO,CAAC,MAAM,CAoChB,CAAC;AAEF;;GAEG;AACH,eAAO,MAAM,OAAO,GAAU,QAAQ,MAAM,EAAE,WAAW,MAAM,EAAE,YAAY,MAAM,KAAG,OAAO,CAAC,OAAO,CAsCpG,CAAC"}

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;IACvB,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE;QAC9B,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;YAC/B,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;QAC3B,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,EAAE;YAC/B,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;QAC3B,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE;YACzB,OAAO,CAAC;gBACP,MAAM;gBACN,MAAM;gBACN,QAAQ,EAAE,IAAI,IAAI,CAAC;aACnB,CAAC,CAAC;QACJ,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,EAAE;YACxB,OAAO,CAAC;gBACP,MAAM;gBACN,MAAM,EAAE,GAAG,CAAC,OAAO;gBACnB,QAAQ,EAAE,CAAC;aACX,CAAC,CAAC;QACJ,CAAC,CAAC,CAAC;IACJ,CAAC,CAAC,CAAC;AACJ,CAAC,CAAC;AAEF;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAG,KAAK,EACjC,MAAc,EACd,OAAe,EACf,OAAuE,EACrD,EAAE;IACpB,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE;QAC9B,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;YACzB,OAAO,CAAC,IAAI,IAAI,CAAC,CAAC,CAAC;QACpB,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE;YACrB,OAAO,CAAC,CAAC,CAAC,CAAC;QACZ,CAAC,CAAC,CAAC;IACJ,CAAC,CAAC,CAAC;AACJ,CAAC,CAAC;AAEF;;GAEG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,KAAK,EAAE,MAAc,EAAE,SAAiB,EAAE,UAAkB,EAAoB,EAAE;IACxG,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;QAC9B,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;YACzB,OAAO,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC;QACrB,CAAC,CAAC,CAAC;QAEH,IAAI,CAAC,EAAE,CAAC,OAAO,EAAE,GAAG,EAAE;YACrB,OAAO,CAAC,KAAK,CAAC,CAAC;QAChB,CAAC,CAAC,CAAC;IACJ,CAAC,CAAC,CAAC;AACJ,CAAC,CAAC"}

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"}

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"}

package/package.json

@@ -1,42 +1,40 @@
 {
-  "name": "@mariozechner/pi",
-  "version": "0.1.5",
-  "description": "CLI tool for managing vLLM deployments on GPU pods from Prime Intellect, Vast.ai, etc.",
-  "main": "pi.js",
-  "bin": {
-    "pi": "pi.js"
-  },
-  "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1"
-  },
-  "keywords": [
-    "llm",
-    "vllm",
-    "gpu",
-    "prime-intellect",
-    "ai",
-    "ml",
-    "cli"
-  ],
-  "author": "Mario Zechner",
-  "license": "MIT",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/badlogic/pi.git"
-  },
-  "bugs": {
-    "url": "https://github.com/badlogic/pi/issues"
-  },
-  "homepage": "https://github.com/badlogic/pi#readme",
-  "engines": {
-    "node": ">=14.0.0"
-  },
-  "preferGlobal": true,
-  "files": [
-    "pi.js",
-    "pod_setup.sh",
-    "vllm_manager.py",
-    "README.md",
-    "LICENSE"
-  ]
+	"name": "@mariozechner/pi",
+	"version": "0.5.0",
+	"description": "CLI tool for managing vLLM deployments on GPU pods",
+	"type": "module",
+	"bin": {
+		"pi": "dist/cli.js"
+	},
+	"scripts": {
+		"clean": "rm -rf dist",
+		"build": "tsc -p tsconfig.build.json && chmod +x dist/cli.js && cp src/models.json dist/",
+		"check": "biome check --write .",
+		"prepublishOnly": "npm run clean && npm run build"
+	},
+	"files": [
+		"dist"
+	],
+	"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": {
+		"@mariozechner/pi-agent": "^0.5.0",
+		"chalk": "^5.5.0"
+	},
+	"devDependencies": {}
 }

package/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2025 Mario Zechner
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.