replicate/cog
Containers for machine learning
Generates optimized Docker images from simple YAML configuration, automatically handling CUDA/dependency compatibility and GPU setup. Defines model inputs/outputs as Python types to automatically create OpenAPI schemas and a high-performance Rust/Axum HTTP prediction server. Packages models for local testing or production deployment to any Docker-compatible infrastructure.
9,268 stars. Actively maintained with 69 commits in the last 30 days. Available on PyPI.
Stars
9,268
Forks
657
Language
Go
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
69
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/replicate/cog"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
dusty-nv/jetson-containers
Machine Learning Containers for NVIDIA Jetson and JetPack-L4T
rsnk96/Ubuntu-Setup-Scripts
Scripts to help you set up your Ubuntu quickly, especially if you're in any subfield of Data...
open-ce/open-ce
This repository provides the Open-CE environment files and version definitions for each Open-CE release.
quantbelt/jupyter-quant
A dockerized Jupyter quant research environment.
lablup/backend.ai-kernels
Repository of Backend.AI-enabled container recipes