sajidkhan2067/LLMOnAWS

Deploy smaller LLM on AWS Lambda: Phi-2, cost-effective language model

25
/ 100
Experimental

This project helps developers and MLOps engineers deploy smaller large language models (LLMs) like Microsoft Phi-2 onto AWS Lambda for cost-effective inference. It takes an open-source LLM and Docker configuration as input, and outputs a deployed, functional LLM endpoint on AWS Lambda. This is for users who need to run custom LLMs in a serverless environment, often due to data sensitivity or specific language requirements.

No commits in the last 6 months.

Use this if you are a developer or MLOps engineer looking for a cost-efficient way to host smaller open-source LLMs on a serverless AWS infrastructure.

Not ideal if you prefer managed LLM services or do not have experience with AWS, Docker, and Python development.

serverless-ml llm-deployment aws-lambda mlops custom-ai-models
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Shell

License

Last pushed

Feb 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sajidkhan2067/LLMOnAWS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.