{ "input_model": { "type": "PyTorchModel", "config": { "model_path": "", "model_loader": "text_encoder_load", "model_script": "modules/onnx.py", "io_config": { "input_names": ["input_ids"], "output_names": ["last_hidden_state", "pooler_output"], "dynamic_axes": { "input_ids": { "0": "batch", "1": "sequence" } } }, "dummy_inputs_func": "text_encoder_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/onnx.py", "dataloader_func": "text_encoder_data_loader", "batch_size": 1 } } ] } }, "passes": { "convert": { "type": "OnnxConversion", "config": { "target_opset": 14 } }, "optimize": { "type": "OrtTransformersOptimization", "disable_search": true, "config": { "model_type": "clip", "float16": true, "use_gpu": true, "keep_io_types": false, "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_fp16_inputs": { "GroupNorm": [0, 1, 2] } }, "force_fp32_ops": ["RandomNormalLike"] } } }, "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": "text_encoder", "output_dir": "footprints", "execution_providers": ["DmlExecutionProvider"] } }