serving.json

{
  "external_data": "model.onnx.data",
  "geometry": {
    "dynamic_batch": true,
    "dynamic_sequence": true,
    "local_attention_window": 257,
    "max_batch": 32,
    "max_sequence": 1024,
    "passage_max_sequence": 1024,
    "query_max_sequence": 128
  },
  "graph": "model.onnx",
  "inputs": [
    "input_ids",
    "attention_mask"
  ],
  "output": "embeddings",
  "precision": "float32",
  "provider_chain": [
    "CUDAExecutionProvider",
    "CPUExecutionProvider"
  ],
  "role": "dense-retriever",
  "schema": "daecore.retrieval-onnx-serving.v1",
  "sha256": "8c088b1635875d5406e148782b303cfc5a961138600783fb4842b413b98a98c3",
  "source_model_tree_sha256": "30a7b9f1c42b1fcee29a6729742685d5b744e8fa87d13cefab2fd2d49ea9150e",
  "torch_required_at_runtime": false
}