https://github.com/abm1499/elastic-ml-inference-serving
A cloud computing project featuring an elastic inference system for ResNet-18 using Kubernetes, Flask, and PyTorch. Includes a custom autoscaler (30% latency reduction), Prometheus monitoring, and load testing.
https://github.com/abm1499/elastic-ml-inference-serving
docker flask hpa kubernetes kubernetes-cluster kubernetes-deployment machine-learning minikube minikube-cluster ml prometheus python pytorch resnet-18
Last synced: 3 months ago
JSON representation
A cloud computing project featuring an elastic inference system for ResNet-18 using Kubernetes, Flask, and PyTorch. Includes a custom autoscaler (30% latency reduction), Prometheus monitoring, and load testing.
- Host: GitHub
- URL: https://github.com/abm1499/elastic-ml-inference-serving
- Owner: abm1499
- Created: 2024-06-06T14:07:15.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2025-03-13T11:30:32.000Z (over 1 year ago)
- Last Synced: 2025-03-13T12:31:58.337Z (over 1 year ago)
- Topics: docker, flask, hpa, kubernetes, kubernetes-cluster, kubernetes-deployment, machine-learning, minikube, minikube-cluster, ml, prometheus, python, pytorch, resnet-18
- Language: Python
- Homepage:
- Size: 101 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md