# w-train-utils-mlflow-triton-plugin
## 가상환경 설정
```sh
pyenv install 3.8.18
pyenv virtualenv 3.8.18 wtrainclient3.8
pyenv activate wtrainclient3.8
```
---
## Triton Inference Server 실행
```sh
$ docker run --rm -p8000:8000 -p8001:8001 -p8002:8002 \
-e AWS_ACCESS_KEY_ID=<AccessKey> \
-e AWS_SECRET_ACCESS_KEY=<SecretKey> \
nvcr.io/nvidia/tritonserver:24.01-py3 \
tritonserver --model-repository=s3://https://kitech-minio-api.wimcorp.dev:443/triton \
--model-control-mode=explicit \
--log-verbose=1
```
---
## 환경 변수 설정
프로젝트를 실행하기 전에 아래의 환경 변수들을 설정해야 합니다:
| 환경변수 | 설명 | 예시 |
| ---------------------- | --------------------------------------------------- | --------------------------------- |
| MLFLOW_S3_ENDPOINT_URL | MLflow가 저장소로 사용하고있는 MinIO 엔드포인트 URL | http://localhost:9000 |
| MLFLOW_TRACKING_URI | MLflow 트래킹 서버의 URI | http://localhost:5001 |
| AWS_ACCESS_KEY_ID | MinIO 서버 접근을 위한 AWS 호환 액세스 키 | minio |
| AWS_SECRET_ACCESS_KEY | MinIO 서버 접근을 위한 AWS 호환 시크릿 액세스 키 | miniostorage |
| TRITON_URL | Triton Inference Server 의 grpc 엔드포인트 URL | http://localhost:8001 |
| TRITON_MODEL_REPO | Triton Inference Server 의 모델저장소 URL | s3://http://localhost:9000/triton |
---
## 패키지 빌드 및 업로드
```sh
# 필요한 의존성 설치
pip install wheel setuptools twine
```
```sh
vi ~/.pypirc
[distutils]
index-servers =
pypi
pypi-repository
[pypi]
username = __token__
password = <token>
[pypi-repository]
repository: https://<domain>/repository/<pypi-hosted>/
username: <username>
password: <password>
```
```sh
sh scripts/build.sh
sh scripts/deploy.sh
```
Raw data
{
"_id": null,
"home_page": "https://github.com/WIM-Corporation/w-train-utils-mlflow-triton-plugin",
"name": "wtu-mlflow-triton-plugin",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": null,
"author": "hbjs",
"author_email": "hbjs97@naver.com",
"download_url": "https://files.pythonhosted.org/packages/62/4b/cbed4f01ae5d92ed2ec8d48cafae8ca8fa76a64fe08f4a7a1ee60fc92821/wtu-mlflow-triton-plugin-0.0.15.tar.gz",
"platform": null,
"description": "# w-train-utils-mlflow-triton-plugin\n\n## \uac00\uc0c1\ud658\uacbd \uc124\uc815\n\n```sh\npyenv install 3.8.18\npyenv virtualenv 3.8.18 wtrainclient3.8\npyenv activate wtrainclient3.8\n```\n\n---\n\n## Triton Inference Server \uc2e4\ud589\n\n```sh\n$ docker run --rm -p8000:8000 -p8001:8001 -p8002:8002 \\\n -e AWS_ACCESS_KEY_ID=<AccessKey> \\\n -e AWS_SECRET_ACCESS_KEY=<SecretKey> \\\n nvcr.io/nvidia/tritonserver:24.01-py3 \\\n tritonserver --model-repository=s3://https://kitech-minio-api.wimcorp.dev:443/triton \\\n --model-control-mode=explicit \\\n --log-verbose=1\n```\n\n---\n\n## \ud658\uacbd \ubcc0\uc218 \uc124\uc815\n\n\ud504\ub85c\uc81d\ud2b8\ub97c \uc2e4\ud589\ud558\uae30 \uc804\uc5d0 \uc544\ub798\uc758 \ud658\uacbd \ubcc0\uc218\ub4e4\uc744 \uc124\uc815\ud574\uc57c \ud569\ub2c8\ub2e4:\n\n| \ud658\uacbd\ubcc0\uc218 | \uc124\uba85 | \uc608\uc2dc |\n| ---------------------- | --------------------------------------------------- | --------------------------------- |\n| MLFLOW_S3_ENDPOINT_URL | MLflow\uac00 \uc800\uc7a5\uc18c\ub85c \uc0ac\uc6a9\ud558\uace0\uc788\ub294 MinIO \uc5d4\ub4dc\ud3ec\uc778\ud2b8 URL | http://localhost:9000 |\n| MLFLOW_TRACKING_URI | MLflow \ud2b8\ub798\ud0b9 \uc11c\ubc84\uc758 URI | http://localhost:5001 |\n| AWS_ACCESS_KEY_ID | MinIO \uc11c\ubc84 \uc811\uadfc\uc744 \uc704\ud55c AWS \ud638\ud658 \uc561\uc138\uc2a4 \ud0a4 | minio |\n| AWS_SECRET_ACCESS_KEY | MinIO \uc11c\ubc84 \uc811\uadfc\uc744 \uc704\ud55c AWS \ud638\ud658 \uc2dc\ud06c\ub9bf \uc561\uc138\uc2a4 \ud0a4 | miniostorage |\n| TRITON_URL | Triton Inference Server \uc758 grpc \uc5d4\ub4dc\ud3ec\uc778\ud2b8 URL | http://localhost:8001 |\n| TRITON_MODEL_REPO | Triton Inference Server \uc758 \ubaa8\ub378\uc800\uc7a5\uc18c URL | s3://http://localhost:9000/triton |\n\n---\n\n## \ud328\ud0a4\uc9c0 \ube4c\ub4dc \ubc0f \uc5c5\ub85c\ub4dc\n\n```sh\n# \ud544\uc694\ud55c \uc758\uc874\uc131 \uc124\uce58\npip install wheel setuptools twine\n```\n\n```sh\nvi ~/.pypirc\n\n[distutils]\nindex-servers =\n pypi\n pypi-repository\n\n[pypi]\n username = __token__\n password = <token>\n\n[pypi-repository]\nrepository: https://<domain>/repository/<pypi-hosted>/\nusername: <username>\npassword: <password>\n```\n\n```sh\nsh scripts/build.sh\nsh scripts/deploy.sh\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "W-Train Utils for MLflow Triton Plugin",
"version": "0.0.15",
"project_urls": {
"Homepage": "https://github.com/WIM-Corporation/w-train-utils-mlflow-triton-plugin"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a4480f2be6b932e72f2a02fb74a6914b3fd30cc53cb5e680a6bb6686144e718b",
"md5": "1cbd2873e6236e4842566c7a511580f7",
"sha256": "912b3339a6613500bb1f00ca7ac3bedd46e1bab20ada915a316fa0cd8399981f"
},
"downloads": -1,
"filename": "wtu_mlflow_triton_plugin-0.0.15-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1cbd2873e6236e4842566c7a511580f7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 13260,
"upload_time": "2024-10-30T10:43:32",
"upload_time_iso_8601": "2024-10-30T10:43:32.589020Z",
"url": "https://files.pythonhosted.org/packages/a4/48/0f2be6b932e72f2a02fb74a6914b3fd30cc53cb5e680a6bb6686144e718b/wtu_mlflow_triton_plugin-0.0.15-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "624bcbed4f01ae5d92ed2ec8d48cafae8ca8fa76a64fe08f4a7a1ee60fc92821",
"md5": "95e28079f3abd8a3b75535e74127132b",
"sha256": "e6d1db9bc3de31f8ee2ef0ec2e612c92f4be6a9cb41da39de5d6b6840693db59"
},
"downloads": -1,
"filename": "wtu-mlflow-triton-plugin-0.0.15.tar.gz",
"has_sig": false,
"md5_digest": "95e28079f3abd8a3b75535e74127132b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 11673,
"upload_time": "2024-10-30T10:43:33",
"upload_time_iso_8601": "2024-10-30T10:43:33.845610Z",
"url": "https://files.pythonhosted.org/packages/62/4b/cbed4f01ae5d92ed2ec8d48cafae8ca8fa76a64fe08f4a7a1ee60fc92821/wtu-mlflow-triton-plugin-0.0.15.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-30 10:43:33",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "WIM-Corporation",
"github_project": "w-train-utils-mlflow-triton-plugin",
"github_not_found": true,
"lcname": "wtu-mlflow-triton-plugin"
}
JSON
