{
  "input_model": {
    "type": "PyTorchModel",
    "config": {
      "model_path": "",
      "model_loader": "unet_load",
      "model_script": "modules/olive_script.py",
      "io_config": {
        "input_names": [
          "sample",
          "timestep",
          "encoder_hidden_states",
          "text_embeds",
          "time_ids"
        ],
        "output_names": ["out_sample"],
        "dynamic_axes": {
          "sample": {
            "0": "unet_sample_batch",
            "1": "unet_sample_channels",
            "2": "unet_sample_height",
            "3": "unet_sample_width"
          },
          "timestep": { "0": "unet_time_batch" },
          "encoder_hidden_states": {
            "0": "unet_hidden_batch",
            "1": "unet_hidden_sequence"
          },
          "text_embeds": {
            "0": "unet_text_embeds_batch",
            "1": "unet_text_embeds_size"
          },
          "time_ids": { "0": "unet_time_ids_batch", "1": "unet_time_ids_size" }
        }
      },
      "dummy_inputs_func": "unet_conversion_inputs"
    }
  },
  "systems": {
    "local_system": {
      "type": "LocalSystem",
      "config": {
        "accelerators": ["gpu"]
      }
    }
  },
  "evaluators": {
    "common_evaluator": {
      "metrics": [
        {
          "name": "latency",
          "type": "latency",
          "sub_types": [{ "name": "avg" }],
          "user_config": {
            "user_script": "modules/olive_script.py",
            "dataloader_func": "unet_data_loader",
            "batch_size": 2
          }
        }
      ]
    }
  },
  "passes": {
    "optimize_DmlExecutionProvider": {
      "type": "OrtTransformersOptimization",
      "disable_search": true,
      "config": {
        "model_type": "unet",
        "opt_level": 0,
        "float16": true,
        "use_gpu": true,
        "keep_io_types": true,
        "optimization_options": {
          "enable_gelu": true,
          "enable_layer_norm": true,
          "enable_attention": true,
          "use_multi_head_attention": true,
          "enable_skip_layer_norm": false,
          "enable_embed_layer_norm": true,
          "enable_bias_skip_layer_norm": false,
          "enable_bias_gelu": true,
          "enable_gelu_approximation": false,
          "enable_qordered_matmul": false,
          "enable_shape_inference": true,
          "enable_gemm_fast_gelu": false,
          "enable_nhwc_conv": false,
          "enable_group_norm": true,
          "enable_bias_splitgelu": false,
          "enable_packed_qkv": true,
          "enable_packed_kv": true,
          "enable_bias_add": false,
          "group_norm_channels_last": false
        },
        "force_fp32_ops": ["RandomNormalLike"],
        "force_fp16_inputs": {
          "GroupNorm": [0, 1, 2]
        }
      }
    },
    "optimize_CUDAExecutionProvider": {
      "type": "OrtTransformersOptimization",
      "disable_search": true,
      "config": {
        "model_type": "unet",
        "opt_level": 0,
        "float16": true,
        "use_gpu": true,
        "keep_io_types": true
      }
    },
    "optimize_ROCMExecutionProvider": {
      "type": "OrtTransformersOptimization",
      "disable_search": true,
      "config": {
        "model_type": "unet",
        "opt_level": 0,
        "float16": true,
        "use_gpu": true,
        "keep_io_types": true
      }
    }
  },
  "pass_flows": [["optimize_AutoExecutionProvider"]],
  "engine": {
    "search_strategy": {
      "execution_order": "joint",
      "search_algorithm": "exhaustive"
    },
    "evaluator": "common_evaluator",
    "evaluate_input_model": false,
    "host": "local_system",
    "target": "local_system",
    "cache_dir": "cache",
    "output_name": "unet",
    "output_dir": "footprints",
    "execution_providers": ["DmlExecutionProvider"]
  }
}