{
  "model_name": "Nemotron 3.5 Parse",
  "repository": "nvidia/Nemotron-3.5-Parse",
  "release_date": "2026-10-17",
  "license": "OpenMDW-1.1",
  "model_release": "3.5.0",
  "plugin_release": "3.5.0.post7",
  "unique_parameters": 630800496,
  "mtp_parameters": 2099200,
  "model_safetensors_sha256": "81dd7609c589f3694ce75520c25af5010953231358de6aec4d03e8c6aac787e9",
  "runtime_defaults": {
    "one_token_mtp": true,
    "fa3_aot_scheduler": false,
    "model_scoped": true,
    "explicit_speculative_options_respected": true
  },
  "attention_backend_source_pin": {
    "backend": "FlashAttention FA3",
    "provided_by": "vllm==0.26.0",
    "standalone_flash_attn_distribution": false,
    "flash_attention_source_version": "2.8.4",
    "repository": "https://github.com/vllm-project/flash-attention",
    "revision": "caaa4eb59845388a20b1f435ecaafb4bd9517ad8",
    "pin_evidence": "https://github.com/vllm-project/vllm/blob/v0.26.0/cmake/external_projects/vllm_flash_attn.cmake",
    "scope": "Upstream default source pin for vLLM 0.26.0; not a new runtime measurement"
  },
  "validation_status": "Current package runtime matches the GPU-tested post5 source; post6 adds timing instrumentation, post7 updates notices. See reference/validation and reference/package for exact scope and artifact identities.",
  "previous_release_validation": {
    "model_release": "3.5.0rc3",
    "plugin_release": "3.5.0rc3",
    "model_safetensors_sha256": "fa5980193d8519efbdcd45054f3a7616c961d06f7a7653bdafcfba60a412f09c",
    "wheel_sha256": "20d3a4504c1a74cac4b403f7afd72d77ce07d5c335993bb5fb53a44c164a0171",
    "validated_runtime": {
      "vllm": "0.26.0",
      "transformers": "5.14.1",
      "huggingface-hub": "1.24.0",
      "torch": "2.11.0",
      "torchvision": "0.26.0",
      "timm": "1.0.22",
      "nemotron-parse": "3.5.0rc3"
    },
    "validation_reference": "reference/parse_3_5/validation.json"
  },
  "installation": "Repository source: python -m pip install \".[vllm,client]\""
}