@aws/ml-container-creator 0.9.0 → 0.10.0

package/src/lib/generated/cli-options.js

@@ -0,0 +1,471 @@
+// AUTO-GENERATED by scripts/codegen-cli.js — DO NOT EDIT
+// Source: config/parameter-schema-v2.json
+// Generated: 2026-05-23T12:02:19.426Z
+
+/**
+ * CLI option definitions derived from parameter-schema-v2.json.
+ * Each entry can be registered with Commander via:
+ *   new Option(entry.flag, entry.description)
+ */
+export const cliOptions = [
+    {
+        "flag": "--project-name <name>",
+        "description": "Name for the generated project"
+    },
+    {
+        "flag": "--deployment-config <config>",
+        "description": "Deployment configuration (e.g. http-flask, transformers-vllm, triton-fil)",
+        "choices": [
+            "http-flask",
+            "http-fastapi",
+            "transformers-vllm",
+            "transformers-sglang",
+            "transformers-tensorrt-llm",
+            "transformers-lmi",
+            "transformers-djl",
+            "triton-fil",
+            "triton-onnxruntime",
+            "triton-tensorflow",
+            "triton-pytorch",
+            "triton-vllm",
+            "triton-tensorrtllm",
+            "triton-python",
+            "diffusors-vllm-omni",
+            "marketplace"
+        ]
+    },
+    {
+        "flag": "--model-name <name>",
+        "description": "Model identifier (hf-org/model, s3://..., registry://..., marketplace://...)"
+    },
+    {
+        "flag": "--deployment-target <target>",
+        "description": "Deployment target (managed-inference, async-inference, batch-transform, hyperpod-eks)",
+        "choices": [
+            "managed-inference",
+            "realtime-inference",
+            "async-inference",
+            "batch-transform",
+            "hyperpod-eks"
+        ],
+        "defaultValue": "realtime-inference"
+    },
+    {
+        "flag": "--instance-type <type>",
+        "description": "SageMaker instance type (e.g. ml.g5.xlarge, ml.m5.large)"
+    },
+    {
+        "flag": "--ic-gpu-count <n>",
+        "description": "GPUs allocated to the inference component"
+    },
+    {
+        "flag": "--ic-copy-count <n>",
+        "description": "Number of inference component copies",
+        "defaultValue": 1
+    },
+    {
+        "flag": "--ic-memory-size <mb>",
+        "description": "Memory in MB for the inference component",
+        "defaultValue": 1024
+    },
+    {
+        "flag": "--enable-lora",
+        "description": "Enable LoRA adapter serving",
+        "defaultValue": false
+    },
+    {
+        "flag": "--max-loras <n>",
+        "description": "Maximum concurrent LoRA adapters in GPU memory",
+        "defaultValue": 30
+    },
+    {
+        "flag": "--max-lora-rank <n>",
+        "description": "Maximum LoRA rank",
+        "defaultValue": 64
+    },
+    {
+        "flag": "--include-benchmark",
+        "description": "Include SageMaker AI Benchmarking",
+        "defaultValue": false
+    },
+    {
+        "flag": "--benchmark-concurrency <n>",
+        "description": "Benchmark concurrent requests",
+        "defaultValue": 10
+    },
+    {
+        "flag": "--benchmark-input-tokens <n>",
+        "description": "Benchmark mean input tokens",
+        "defaultValue": 550
+    },
+    {
+        "flag": "--benchmark-output-tokens <n>",
+        "description": "Benchmark mean output tokens",
+        "defaultValue": 150
+    },
+    {
+        "flag": "--benchmark-streaming",
+        "description": "Enable streaming in benchmark",
+        "defaultValue": true
+    },
+    {
+        "flag": "--benchmark-request-count <n>",
+        "description": "Total number of benchmark requests to send"
+    },
+    {
+        "flag": "--benchmark-s3-output-path <path>",
+        "description": "S3 URI for benchmark results output"
+    },
+    {
+        "flag": "--skip-prompts",
+        "description": "Skip interactive prompts and use configuration from other sources",
+        "defaultValue": false
+    },
+    {
+        "flag": "--auto-prompt",
+        "description": "Fill defaults, prompt only for missing required values",
+        "defaultValue": false
+    },
+    {
+        "flag": "--config <path>",
+        "description": "Path to JSON configuration file"
+    },
+    {
+        "flag": "--project-dir <dir>",
+        "description": "Output directory path"
+    },
+    {
+        "flag": "--force",
+        "description": "Overwrite existing output directory without prompting",
+        "defaultValue": false
+    },
+    {
+        "flag": "--framework <framework>",
+        "description": "ML framework",
+        "choices": [
+            "sklearn",
+            "xgboost",
+            "tensorflow",
+            "transformers"
+        ],
+        "hidden": true
+    },
+    {
+        "flag": "--model-format <format>",
+        "description": "Model serialization format (pkl, joblib, json, model, ubj, keras, h5, SavedModel)",
+        "choices": [
+            "pkl",
+            "joblib",
+            "json",
+            "model",
+            "ubj",
+            "keras",
+            "h5",
+            "SavedModel"
+        ]
+    },
+    {
+        "flag": "--model-server <server>",
+        "description": "Model server",
+        "choices": [
+            "flask",
+            "fastapi",
+            "vllm",
+            "sglang"
+        ],
+        "hidden": true
+    },
+    {
+        "flag": "--base-image <image>",
+        "description": "Base container image for Dockerfile"
+    },
+    {
+        "flag": "--region <region>",
+        "description": "AWS region",
+        "defaultValue": "us-east-1"
+    },
+    {
+        "flag": "--role-arn <arn>",
+        "description": "IAM role ARN for SageMaker execution"
+    },
+    {
+        "flag": "--build-target <target>",
+        "description": "Build target (codebuild)",
+        "choices": [
+            "codebuild"
+        ]
+    },
+    {
+        "flag": "--codebuild-compute-type <type>",
+        "description": "CodeBuild compute type (SMALL, MEDIUM, LARGE)",
+        "choices": [
+            "SMALL",
+            "MEDIUM",
+            "LARGE",
+            "BUILD_GENERAL1_SMALL",
+            "BUILD_GENERAL1_MEDIUM",
+            "BUILD_GENERAL1_LARGE",
+            "BUILD_GENERAL1_2XLARGE"
+        ],
+        "defaultValue": "BUILD_GENERAL1_LARGE"
+    },
+    {
+        "flag": "--hf-token <token>",
+        "description": "HuggingFace token (or $HF_TOKEN for env var reference)"
+    },
+    {
+        "flag": "--hf-token-arn <arn>",
+        "description": "HuggingFace token ARN from Secrets Manager"
+    },
+    {
+        "flag": "--ngc-token <token>",
+        "description": "NVIDIA NGC token (or $NGC_API_KEY for env var reference)"
+    },
+    {
+        "flag": "--ngc-token-arn <arn>",
+        "description": "NVIDIA NGC token ARN from Secrets Manager"
+    },
+    {
+        "flag": "--endpoint-initial-instance-count <n>",
+        "description": "Number of instances for the endpoint",
+        "defaultValue": 1
+    },
+    {
+        "flag": "--endpoint-data-capture-percent <pct>",
+        "description": "Data capture percentage for monitoring, 0-100",
+        "defaultValue": 0
+    },
+    {
+        "flag": "--endpoint-variant-name <name>",
+        "description": "Production variant name",
+        "defaultValue": "AllTraffic"
+    },
+    {
+        "flag": "--endpoint-volume-size <gb>",
+        "description": "ML storage volume size in GB"
+    },
+    {
+        "flag": "--ic-cpu-count <n>",
+        "description": "vCPUs allocated to the inference component"
+    },
+    {
+        "flag": "--ic-model-weight <weight>",
+        "description": "Traffic routing weight, 0-1",
+        "defaultValue": 1
+    },
+    {
+        "flag": "--async-s3-output-path <path>",
+        "description": "S3 output path for async results"
+    },
+    {
+        "flag": "--async-sns-success-topic <arn>",
+        "description": "SNS topic ARN for success notifications"
+    },
+    {
+        "flag": "--async-sns-error-topic <arn>",
+        "description": "SNS topic ARN for error notifications"
+    },
+    {
+        "flag": "--async-max-concurrent <n>",
+        "description": "Max concurrent invocations per instance",
+        "defaultValue": 1
+    },
+    {
+        "flag": "--batch-input-path <path>",
+        "description": "S3 input path for batch data"
+    },
+    {
+        "flag": "--batch-output-path <path>",
+        "description": "S3 output path for batch results"
+    },
+    {
+        "flag": "--batch-instance-count <n>",
+        "description": "Number of batch instances",
+        "defaultValue": 1
+    },
+    {
+        "flag": "--batch-split-type <type>",
+        "description": "Input split type: Line, RecordIO, None",
+        "choices": [
+            "Line",
+            "RecordIO",
+            "None"
+        ],
+        "defaultValue": "Line"
+    },
+    {
+        "flag": "--batch-strategy <strategy>",
+        "description": "Batch strategy: MultiRecord, SingleRecord",
+        "choices": [
+            "MultiRecord",
+            "SingleRecord"
+        ],
+        "defaultValue": "MultiRecord"
+    },
+    {
+        "flag": "--batch-join-source <source>",
+        "description": "Join source: Input, None",
+        "choices": [
+            "Input",
+            "None"
+        ],
+        "defaultValue": "None"
+    },
+    {
+        "flag": "--batch-max-concurrent <n>",
+        "description": "Max concurrent transforms per instance",
+        "defaultValue": 1
+    },
+    {
+        "flag": "--batch-max-payload <mb>",
+        "description": "Max payload size in MB, 0-100",
+        "defaultValue": 6
+    },
+    {
+        "flag": "--hyperpod-cluster <name>",
+        "description": "HyperPod EKS cluster name"
+    },
+    {
+        "flag": "--hyperpod-namespace <ns>",
+        "description": "Kubernetes namespace",
+        "defaultValue": "default"
+    },
+    {
+        "flag": "--hyperpod-replicas <count>",
+        "description": "Number of replicas",
+        "defaultValue": 1
+    },
+    {
+        "flag": "--fsx-volume-handle <handle>",
+        "description": "FSx for Lustre volume handle"
+    },
+    {
+        "flag": "--model-env <KEY=VALUE>",
+        "description": "Model env var, repeatable (e.g. VLLM_TENSOR_PARALLEL_SIZE=4)",
+        "repeatable": true
+    },
+    {
+        "flag": "--server-env <KEY=VALUE>",
+        "description": "Server env var, repeatable (e.g. SGLANG_MEM_FRACTION=0.9)",
+        "repeatable": true
+    },
+    {
+        "flag": "--include-sample",
+        "description": "Include sample model code",
+        "defaultValue": true
+    },
+    {
+        "flag": "--include-testing",
+        "description": "Include test suite",
+        "defaultValue": true
+    },
+    {
+        "flag": "--test-types <types>",
+        "description": "Comma-separated test types"
+    },
+    {
+        "flag": "--smart",
+        "description": "Enable smart mode (live AWS API calls for MCP servers)",
+        "defaultValue": false
+    },
+    {
+        "flag": "--discover",
+        "description": "Enable discovery mode for MCP servers",
+        "defaultValue": false
+    },
+    {
+        "flag": "--no-validate",
+        "description": "Skip parameter validation",
+        "defaultValue": false
+    },
+    {
+        "flag": "--validate-env-vars",
+        "description": "Validate environment variables against schema",
+        "defaultValue": false
+    },
+    {
+        "flag": "--validate-with-docker",
+        "description": "Validate Dockerfile builds successfully",
+        "defaultValue": false
+    },
+    {
+        "flag": "--offline",
+        "description": "Run in offline mode (no network calls)",
+        "defaultValue": false
+    }
+];
+
+/**
+ * Maps CLI flags to help section groups.
+ * Used by the custom help formatter in bin/cli.js.
+ */
+export const helpGroups = {
+    "--project-name": "general",
+    "--deployment-config": "model",
+    "--model-name": "model",
+    "--deployment-target": "infra",
+    "--instance-type": "infra",
+    "--ic-gpu-count": "ic",
+    "--ic-copy-count": "ic",
+    "--ic-memory-size": "ic",
+    "--enable-lora": "features",
+    "--max-loras": "features",
+    "--max-lora-rank": "features",
+    "--include-benchmark": "general",
+    "--benchmark-concurrency": "general",
+    "--benchmark-input-tokens": "general",
+    "--benchmark-output-tokens": "general",
+    "--benchmark-streaming": "general",
+    "--benchmark-request-count": "general",
+    "--benchmark-s3-output-path": "general",
+    "--skip-prompts": "general",
+    "--auto-prompt": "general",
+    "--config": "general",
+    "--project-dir": "general",
+    "--force": "general",
+    "--framework": "model",
+    "--model-format": "model",
+    "--model-server": "model",
+    "--base-image": "infra",
+    "--region": "infra",
+    "--role-arn": "infra",
+    "--build-target": "infra",
+    "--codebuild-compute-type": "infra",
+    "--hf-token": "auth",
+    "--hf-token-arn": "auth",
+    "--ngc-token": "auth",
+    "--ngc-token-arn": "auth",
+    "--endpoint-initial-instance-count": "endpoint",
+    "--endpoint-data-capture-percent": "endpoint",
+    "--endpoint-variant-name": "endpoint",
+    "--endpoint-volume-size": "endpoint",
+    "--ic-cpu-count": "ic",
+    "--ic-model-weight": "ic",
+    "--async-s3-output-path": "async",
+    "--async-sns-success-topic": "async",
+    "--async-sns-error-topic": "async",
+    "--async-max-concurrent": "async",
+    "--batch-input-path": "batch",
+    "--batch-output-path": "batch",
+    "--batch-instance-count": "batch",
+    "--batch-split-type": "batch",
+    "--batch-strategy": "batch",
+    "--batch-join-source": "batch",
+    "--batch-max-concurrent": "batch",
+    "--batch-max-payload": "batch",
+    "--hyperpod-cluster": "hyperpod",
+    "--hyperpod-namespace": "hyperpod",
+    "--hyperpod-replicas": "hyperpod",
+    "--fsx-volume-handle": "hyperpod",
+    "--model-env": "env",
+    "--server-env": "env",
+    "--include-sample": "features",
+    "--include-testing": "features",
+    "--test-types": "features",
+    "--smart": "mcp",
+    "--discover": "mcp",
+    "--no-validate": "validation",
+    "--validate-env-vars": "validation",
+    "--validate-with-docker": "validation",
+    "--offline": "validation"
+};