{
  "id": "step37-flash-vllm",
  "title": "Step-3.7-Flash: vLLM recipe",
  "kind": "deployment",
  "source_type": "maintainer_recipe",
  "summary": "Step 3.7 Flash engine recipe with separate BF16, FP8 and NVFP4 artifacts.",
  "runtime": "vLLM",
  "runtime_topics": [
    "vLLM"
  ],
  "hardware_topics": [
    "nvidia"
  ],
  "platform_topics": [
    "linux"
  ],
  "model_label": "Step-3.7-Flash",
  "model_family": "Step",
  "model_id": "stepfun-ai/Step-3.7-Flash",
  "model_release_date": null,
  "model_artifact": {
    "id": "stepfun-ai/Step-3.7-Flash",
    "revision": null,
    "format": "bf16"
  },
  "evidence_state": "source_reported",
  "site_reproduced": false,
  "record_type": "curated_reference",
  "performance_ranking_allowed": false,
  "metrics": null,
  "metrics_status": "site_metrics_unmeasured; attributed_source_figures_in_editorial.reported_results",
  "conditions": {
    "model_revision": null,
    "weight_hash": null,
    "runtime_execution_revision": null,
    "input_tokens": null,
    "output_tokens": null,
    "concurrency": null,
    "cache_state": null,
    "quantization": null,
    "speculative_decoding": null,
    "temperature": null,
    "top_p": null
  },
  "reported_setup": {
    "system": null,
    "node_count": null,
    "parallelism": null,
    "kv_dtype": null,
    "context_limit_tokens": null,
    "experiment_date": null
  },
  "test_profiles": [],
  "deployment_options": [
    {
      "variant": "default",
      "model_id": "stepfun-ai/Step-3.7-Flash",
      "precision": "bf16",
      "supported_hardware": null,
      "model_revision": null,
      "declared_planning_minimum_gb": 475,
      "minimum_runtime_version": "0.23.0",
      "extra_args": [],
      "tensor_parallel_by_hardware": null
    },
    {
      "variant": "fp8",
      "model_id": "stepfun-ai/Step-3.7-Flash-FP8",
      "precision": "fp8",
      "supported_hardware": null,
      "model_revision": null,
      "declared_planning_minimum_gb": 238,
      "minimum_runtime_version": "0.23.0",
      "extra_args": [],
      "tensor_parallel_by_hardware": null
    },
    {
      "variant": "nvfp4",
      "model_id": "stepfun-ai/Step-3.7-Flash-NVFP4",
      "precision": "nvfp4",
      "supported_hardware": null,
      "model_revision": null,
      "declared_planning_minimum_gb": 119,
      "minimum_runtime_version": "0.23.0",
      "extra_args": [
        "--quantization",
        "modelopt",
        "--kv-cache-dtype",
        "fp8",
        "--gpu-memory-utilization",
        "0.9",
        "--async-scheduling"
      ],
      "tensor_parallel_by_hardware": 4
    }
  ],
  "recipe_parameters": {
    "minimum_runtime_version": "0.23.0",
    "nightly_required": false,
    "model_context_limit_tokens": 262144,
    "compatible_strategies": [
      "single_node_tp",
      "single_node_tep",
      "single_node_dep",
      "multi_node_tp",
      "multi_node_tep",
      "multi_node_dep",
      "pd_cluster"
    ],
    "hardware_claims": [
      {
        "profile": "h200",
        "maintainer_status": "verified"
      },
      {
        "profile": "b200",
        "maintainer_status": "verified"
      },
      {
        "profile": "dgx_station_gb300",
        "maintainer_status": "verified"
      }
    ],
    "recipe_updated_on": "2026-05-30",
    "effective_default_minimum_runtime_version": "0.23.0"
  },
  "measurement_scope": "deployment_reference",
  "notes": [
    "Recipe minimum engine version: 0.23.0.",
    "Default artifact: stepfun-ai/Step-3.7-Flash.",
    "Variant and hardware settings are source declarations; select the matching original profile."
  ],
  "limitations": [
    "Consult the selected artifact and source hardware profile together.",
    "Input length, output policy, concurrency and cache are workload-specific; no single benchmark is inferred from the recipe."
  ],
  "comparison_status": "not_comparable",
  "editorial_status": "source_derived_detailed_article",
  "public_benchmark_snapshot": false,
  "source": {
    "publisher": "vllm-project",
    "url": "https://github.com/vllm-project/recipes",
    "repository": "vllm-project/recipes",
    "platform": "github",
    "revision": "d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94",
    "document_path": "models/stepfun-ai/Step-3.7-Flash.yaml",
    "pinned_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml",
    "report_url": null,
    "document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21",
    "last_commit_at": "2026-10-17T09:22:45Z",
    "checked_on": "2026-10-17",
    "metadata_status": "checked"
  },
  "license": {
    "declared_spdx": "Apache-2.0",
    "scope": "Recipe repository only; each model and conversion has independent distribution terms."
  },
  "editorial": {
    "version": 1,
    "published_on": "2026-10-17",
    "modified_on": "2026-10-17",
    "byline": "Run AI Here editorial",
    "creation_method": "AI-assisted source reading and original editorial synthesis; no independent model execution.",
    "answer": "The pinned Step-3.7-Flash recipe defaults to stepfun-ai/Step-3.7-Flash (bf16). Its effective default-variant minimum is vLLM 0.23.0. Select the exact variant, hardware override and topology before treating it as a launch plan. No deployment was run by this site.",
    "sections": [
      {
        "heading": "Which artifact and engine does this recipe select?",
        "paragraphs": [
          "The recipe identifies stepfun-ai/Step-3.7-Flash as its model family entry and selects stepfun-ai/Step-3.7-Flash by default. The default precision label is bf16; model-wide and variant-specific runtime requirements are kept separately below. The document revision fixes what the recipe said, while the weight revision and executed runtime revision remain separate fields. A model-family title alone cannot establish either artifact identity."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57"
        ]
      },
      {
        "heading": "What needs special attention for this model?",
        "paragraphs": [
          "The BF16 route includes expert parallelism and disables cascade attention. Lower-precision variants are different artifacts. The default’s documented multi-GPU recommendation is not evidence of a single-Spark load. Keep reasoning level, parser and expert/tensor parallelism with a reproduction; all alter the workload or execution path."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L19"
        ]
      },
      {
        "heading": "How should the settings be applied?",
        "paragraphs": [
          "Choose one artifact variant and one hardware profile from the original recipe, then resolve its shared, variant, hardware, strategy and optional-feature settings together. The base arguments listed here are only one layer and are deliberately not presented as a complete runnable command. Check any nightly-image requirement and the model’s parsers before loading weights. A context declaration is a model limit, while batched-token and sequence settings control a serving workload."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L82"
        ]
      },
      {
        "heading": "What does the memory number mean?",
        "paragraphs": [
          "The GB figure is the recipe’s declared planning minimum for the selected variant. It is not a site measurement, a universal peak allocation or a promise of maximum context. KV cache, auxiliary/draft models, image encoders, temporary workspace and active requests still require memory. Keep GB and GiB distinct, and use the actual artifact size and runtime allocation for a machine-specific budget."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L60"
        ]
      },
      {
        "heading": "What is needed to reproduce a deployment?",
        "paragraphs": [
          "Save the model and conversion revisions, weight hashes, tokenizer/template, container or runtime digest, device count/topology and complete resolved launch. First check one short public request. For a subsequent measurement, fix input and output counts, concurrency, cache state, warmup, sampling, reasoning effort, repetitions and failures. The declarations on this page are source configuration facts; no throughput or quality outcome follows from them."
        ],
        "citations": [
          "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L95"
        ]
      }
    ],
    "facts": [
      {
        "name": "Architecture",
        "value": "moe",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L26",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Total parameters as counted by recipe",
        "value": "198B",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L27",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Active parameters as counted by recipe",
        "value": "11B",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L28",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Native context declaration (tokens)",
        "value": 262144,
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L29",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Model-wide minimum vLLM",
        "value": "0.23.0",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L21",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Effective default-variant minimum vLLM",
        "value": "0.23.0",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L21",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Default artifact",
        "value": "stepfun-ai/Step-3.7-Flash",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Default precision label",
        "value": "bf16",
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Default planning minimum (GB; recipe declaration)",
        "value": 475,
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L60",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Default variant hardware allowlist",
        "value": null,
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Shared base arguments (incomplete launch)",
        "value": [
          "--trust-remote-code",
          "--enable-expert-parallel",
          "--disable-cascade-attn"
        ],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Declared compatible strategies",
        "value": [
          "single_node_tp",
          "single_node_tep",
          "single_node_dep",
          "multi_node_tp",
          "multi_node_tep",
          "multi_node_dep",
          "pd_cluster"
        ],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Optional feature names",
        "value": [
          "tool_calling",
          "reasoning",
          "spec_decoding"
        ],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      },
      {
        "name": "Features selected by default",
        "value": [
          "spec_decoding"
        ],
        "classification": "recipe_declaration",
        "evidence_url": "https://github.com/vllm-project/recipes/blob/d5fc1f55cee70f4e1944f2dd4f7569cb8276ad94/models/stepfun-ai/Step-3.7-Flash.yaml#L57",
        "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
      }
    ],
    "reported_results": [],
    "source_document_sha256": "77f9f16a2b23acb5d60a4c94361573d96380cd59ec55ddf3b84ab2b991956c21"
  }
}