{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/2"}],"enrichment":{"capability":"Provides standardized FastAPI-based handlers and decorators for deploying ML models (vLLM, TensorRT-LLM) to Amazon SageMaker with unified `/ping` and `/invocations` endpoints.","skillfed_tags":["sagemaker","model-serving","ml-deployment"],"use_cases":["Deploy vLLM or TensorRT-LLM models to SageMaker endpoints with standardized health-check and invocation routes.","Add LoRA adapter support to model inference by injecting adapter IDs from request headers into model calls.","Customize model behavior per deployment (e.g., different preprocessing logic) by writing a simple `model.py` without modifying framework code.","Automatically install and manage model-specific dependencies from a `requirements.txt` in model artifacts before server startup.","Integrate multiple ML frameworks under a single SageMaker hosting standard without writing repetitive endpoint boilerplate."],"what_it_does":"This package standardizes how ML models are deployed to Amazon SageMaker by providing a framework-agnostic Python toolkit built on FastAPI. It handles the boilerplate of setting up `/ping` and `/invocations` endpoints that SageMaker expects, with support for framework integration (vLLM, TensorRT-LLM) via decorators and customer customization via environment variables or custom handler functions. The package also supports LoRA adapter injection, automatic dependency installation from model artifacts, and comprehensive logging and error handling.\n\nTypical use: framework developers register default handlers using `@register_ping_handler` and `@register_invocation_handler` decorators; customers then override behavior by placing a `model.py` script in their model artifact folder with `@custom_ping_handler` or `@custom_invocation_handler` decorators, or by setting environment variables. Handler resolution follows a priority chain (environment variables \u2192 customer decorators \u2192 function discovery \u2192 framework decorators), so customization is straightforward without forking the framework.","worth_installing":"Yes, if you are deploying ML models to Amazon SageMaker and want to avoid writing boilerplate FastAPI handlers. The package is actively maintained, has low install friction, carries a permissive license, and provides real value through decorator-based handler registration and priority-based customization. No known vulnerabilities. Install it as a dependency in your SageMaker container image or framework integration layer."},"id":"model-hosting-container-standards","links":{"html":"https://skillfed.io/packages/model-hosting-container-standards","md":"https://skillfed.io/packages/model-hosting-container-standards.md","pypi":"https://pypi.org/project/model-hosting-container-standards/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-06-15","license_spdx":null,"license_treatment":"permissive","name":"model-hosting-container-standards","python_support":"supports_current","summary":"Python toolkit for standardized model hosting container implementations with Amazon SageMaker integration"},"popularity":{"monthly_downloads":2917196,"position":2824,"tier":"top_5000"},"security":{"n_vulnerabilities":0},"version":"0.1.16"}