---
title: "Discussion on \"Scaling your ML API to One Million Requests per day\" | Hashnode"
description: "Discussion on \"Scaling your ML API to One Million Requests per day\". Master Efficient ML Model Deployment: Optimize, Scale, and Control Your BERT Transformer API with AWS EKS, Ray Serve, and K8s HPA"
url: "https://hashnode.com/posts/scaling-your-ml-api-to-one-million-requests-per-day/668b1e34453c23aee56b0dd8"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Scaling your ML API to One Million Requests per day](https://suvrakamaldas.hashnode.dev/scaling-your-ml-api-to-one-million-requests-per-day?utm_source=hashnode&utm_medium=feed)

Master Efficient ML Model Deployment: Optimize, Scale, and Control Your BERT Transformer API with AWS EKS, Ray Serve, and K8s HPA

Jun 29, 2024 · 8 min read · suvrakamaldas.hashnode.dev  
Read the article

-   [#rayserve](https://hashnode.com/tag/rayserve)
-   [#apis](https://hashnode.com/tag/apis)
-   [#aws](https://hashnode.com/tag/aws)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#fastapi](https://hashnode.com/tag/fastapi)
-   [#pytorch](https://hashnode.com/tag/pytorch)
-   [#onnx](https://hashnode.com/tag/onnx)
-   [#docker](https://hashnode.com/tag/docker)
-   [#k8s](https://hashnode.com/tag/k8s)
-   [#kubernetes](https://hashnode.com/tag/kubernetes)
-   [#hpa](https://hashnode.com/tag/hpa)
-   [#load-balancing](https://hashnode.com/tag/load-balancing)
-   [#yaml](https://hashnode.com/tag/yaml)
-   [#k6](https://hashnode.com/tag/k6)
-   [#postman](https://hashnode.com/tag/postman)

## Written by

[Suvrakamal Das](https://hashnode.com/@suvrakamaldas)

@suvrakamaldas · Kolkata, India

  
[View profile](https://hashnode.com/@suvrakamaldas)

Machine Learning Engineer

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
