Upload ops folder as ops_data

ops_data/http_grpc/export_onnx.py

@@ -0,0 +1,24 @@
+import torch
+import torch.nn as nn
+
+class AddModel(nn.Module):
+    def forward(self, x1, x2):
+        return x1 + x2
+
+model = AddModel()
+x1 = torch.randn(1, 3)
+x2 = torch.randn(1, 3)
+
+torch.onnx.export(
+    model,
+    (x1, x2),
+    "add.onnx",
+    input_names=["x1", "x2"],
+    output_names=["y"],
+    dynamic_axes={
+        "x1": {0: "batch"},
+        "x2": {0: "batch"},
+        "y": {0: "batch"},
+    },
+    opset_version=18,
+)

ops_data/http_grpc/model_repo/add/1/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2580354f1ff3b5aca7b1f8e7edd534ba499a31be7c86c83a63ee6d3cd6319976
+size 1224

ops_data/http_grpc/model_repo/add/config.pbtxt

@@ -0,0 +1,24 @@
+name: "add"
+platform: "onnxruntime_onnx"
+max_batch_size: 8
+
+input [
+  {
+    name: "x1"
+    data_type: TYPE_FP32
+    dims: [3]
+  },
+  {
+    name: "x2"
+    data_type: TYPE_FP32
+    dims: [3]
+  }
+]
+
+output [
+  {
+    name: "y"
+    data_type: TYPE_FP32
+    dims: [3]
+  }
+]

ops_data/http_grpc/run.sh

@@ -0,0 +1,7 @@
+docker run --rm --gpus all \
+  -p8000:8000 \
+  -p8001:8001 \
+  -p8002:8002 \
+  -v $PWD/model_repo:/models \
+  nvcr.io/nvidia/tritonserver:25.04-py3 \
+  tritonserver --model-repository=/models

ops_data/test.ipynb

@@ -0,0 +1,61 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "35abefab",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[5. 7. 9.]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import tritonclient.grpc as grpcclient\n",
+    "\n",
+    "client = grpcclient.InferenceServerClient(\"localhost:8001\")\n",
+    "\n",
+    "x1 = np.array([[1,2,3]], dtype=np.float32)\n",
+    "x2 = np.array([[4,5,6]], dtype=np.float32)\n",
+    "\n",
+    "inputs = [\n",
+    "    grpcclient.InferInput(\"x1\", x1.shape, \"FP32\"),\n",
+    "    grpcclient.InferInput(\"x2\", x2.shape, \"FP32\"),\n",
+    "]\n",
+    "inputs[0].set_data_from_numpy(x1)\n",
+    "inputs[1].set_data_from_numpy(x2)\n",
+    "\n",
+    "outputs = [grpcclient.InferRequestedOutput(\"y\")]\n",
+    "\n",
+    "res = client.infer(\"add\", inputs, outputs=outputs)\n",
+    "print(res.as_numpy(\"y\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "deploy",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}