Skip to main content

Model Serving made Efficient in the Cloud

Project description

框架环境变量

环境变量 说明 默认值
TI_MODEL_DIR 模型路径 /data/model
TI_PREPROCESS_NUMS 预处理进程数 0
TI_INFERENCE_NUMS 推理进程数 1
TI_POSTPROCESS_NUMS 后处理进程数 0
TI_INFERENCE_MAX_BATCH_SIZE 推理Batch数 1

说明

  • 当TI_PREPROCESS_NUMS==0且TI_POSTPROCESS_NUMS==0时;

    model_service.py 文件中preprocess,postpress,predict 函数在一个进程中执行

  • 否则,model_service.py 文件中preprocess, postpress, predict 函数分别处于不同进程中执行,

    load 函数与predict 函数处于同一进程;

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

tinfer-0.1.5-py3-none-any.whl (8.1 kB view details)

Uploaded Python 3

File details

Details for the file tinfer-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: tinfer-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 8.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.18

File hashes

Hashes for tinfer-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 bb9468a4dfff911bda75fdc3cd961bf403c3ec198a84369518d749784f105e54
MD5 4c6670d0514f6af1eaf37ca35bc099c6
BLAKE2b-256 74c7471e356f84799d51f8e05a3f6287bb28b38ceed723fa76d0c8ff40c67188

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page