hongbo-miao/hongbomiao.com

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7871e6ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://github.com/aws/amazon-sagemaker-examples/blob/main/multi-model-endpoints/mme-on-gpu/cv/resnet50_mme_with_gpu.ipynb\n",
    "\n",
    "# Prepare PyTorch Model\n",
    "!docker run \\\n",
    "  --gpus=all \\\n",
    "  --volume=\"${PWD}/workspace:/workspace\" \\\n",
    "  --interactive \\\n",
    "  --tty \\\n",
    "  --rm \\\n",
    "  nvcr.io/nvidia/pytorch:22.07-py3 \\\n",
    "    /bin/bash generate_model_pytorch.sh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3502dd08",
   "metadata": {},
   "outputs": [],
   "source": [
    "!mkdir -p triton-serve-pt/resnet-50/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2b8795a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%writefile triton-serve-pt/resnet-50/config.pbtxt\n",
    "name: \"resnet\"\n",
    "platform: \"pytorch_libtorch\"\n",
    "max_batch_size: 128\n",
    "input {\n",
    "  name: \"INPUT__0\"\n",
    "  data_type: TYPE_FP32\n",
    "  dims: 3\n",
    "  dims: 224\n",
    "  dims: 224\n",
    "}\n",
    "output {\n",
    "  name: \"OUTPUT__0\"\n",
    "  data_type: TYPE_FP32\n",
    "  dims: 1000\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "996e0df3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Prepare TensorRT Model\n",
    "!docker run \\\n",
    "  --gpus=all \\\n",
    "  --volume=\"${PWD}/workspace:/workspace\" \\\n",
    "  --interactive \\\n",
    "  --tty \\\n",
    "  --rm \\\n",
    "  nvcr.io/nvidia/pytorch:22.07-py3 \\\n",
    "    /bin/bash generate_model_trt.sh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0dff45fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "!mkdir -p triton-serve-trt/resnet-50/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c8a19004",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%writefile triton-serve-trt/resnet-50/config.pbtxt\n",
    "name: \"resnet\"\n",
    "platform: \"tensorrt_plan\"\n",
    "max_batch_size: 128\n",
    "input {\n",
    "  name: \"input\"\n",
    "  data_type: TYPE_FP32\n",
    "  dims: 3\n",
    "  dims: 224\n",
    "  dims: 224\n",
    "}\n",
    "output {\n",
    "  name: \"output\"\n",
    "  data_type: TYPE_FP32\n",
    "  dims: 1000\n",
    "}\n",
    "model_warmup {\n",
    "    name: \"bs128 Warmup\"\n",
    "    batch_size: 128\n",
    "    inputs: {\n",
    "        key: \"input\"\n",
    "        value: {\n",
    "            data_type: TYPE_FP32\n",
    "            dims: 3\n",
    "            dims: 224\n",
    "            dims: 224\n",
    "            zero_data: false\n",
    "        }\n",
    "    }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9462a5db2be4503",
   "metadata": {},
   "outputs": [],
   "source": [
    "!mkdir -p triton-serve-pt/resnet-50/1/\n",
    "!mv -f workspace/model.pt triton-serve-pt/resnet-50/1/\n",
    "!tar --directory=triton-serve-pt/ --create --gzip --file resnet_pt_v0.tar.gz resnet-50\n",
    "\n",
    "!mkdir -p triton-serve-trt/resnet-50/1/\n",
    "!mv -f workspace/model.plan triton-serve-trt/resnet-50/1/\n",
    "!tar --directory=triton-serve-trt/ --create --gzip --file resnet_trt_v0.tar.gz resnet-50"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "215f3cdc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Upload to S3\n",
    "\n",
    "import boto3\n",
    "import sagemaker\n",
    "\n",
    "\n",
    "model_name = \"resnet-50\"\n",
    "sagemaker_session = sagemaker.Session(boto_session=boto3.Session())\n",
    "model_uri_pt = sagemaker_session.upload_data(\n",
    "    path=\"resnet_pt_v0.tar.gz\", key_prefix=model_name\n",
    ")\n",
    "model_uri_trt = sagemaker_session.upload_data(\n",
    "    path=\"resnet_trt_v0.tar.gz\", key_prefix=model_name\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "instance_type": "ml.p3.2xlarge",
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}