BestHub
search
Sign in
Tag

Seldon

1 views collected around this technical thread.

DataFunTalk
DataFunTalk
Jan 25, 2022 · Cloud Native

Model Deployment Challenges and a Seldon‑Based Cloud‑Native Solution

This article analyzes the complexities of deploying machine‑learning models in production, outlines the limitations of the existing ABox architecture, and details a comprehensive cloud‑native redesign using Seldon on Kubernetes—including custom HDFS initializers, GPU management, logging, and resource monitoring—to streamline operations and enable unified CPU/GPU model serving.

Cloud NativeGPUKubernetes
0 likes · 12 min read
Model Deployment Challenges and a Seldon‑Based Cloud‑Native Solution
Youzan Coder
Youzan Coder
Jan 17, 2022 · Artificial Intelligence

Model Deployment Challenges and a Seldon‑Based Cloud‑Native Solution

The team replaced the cumbersome ABox deployment stack with Seldon‑based cloud‑native serving on Kubernetes, unifying TensorFlow and other framework models, adding GPU sharing, automated CRUD, per‑model ingress, monitoring, and log collection, achieving scalable, fault‑tolerant, zero‑downtime model deployment.

AI servingCloud NativeGPU
0 likes · 11 min read
Model Deployment Challenges and a Seldon‑Based Cloud‑Native Solution