Questions tagged [aws-lambda]

AWS Lambda is a compute service that lets you run code without the overhead of managing servers.

Filter by
Sorted by
Tagged with
0 votes
0 answers
27 views

AWSWrangler chucksize with data type conversion and conversion to Parquet

I have a lambda function that reads in json files and then converts to parquet from S3. I came across an issue where if the files are greater than 1GB, lambda runs out of memory. I'm using awswrangler ...
nahmed's user avatar
  • 1
1 vote
0 answers
67 views

Deploying a model with GPU and pay-per-inference

I may have the wrong stack exchange. If that's the case, could someone point me to a stack that could help with this. Anyways... My backend employs a sentence transformer model from HuggingFace. Since ...
AlwaysLearning's user avatar
0 votes
0 answers
16 views

Hosting Models on a Serverless-like format, AWS specific but not exclusively

Similar question here Deploy ML Model on AWS, but more detail provided below: If I understand correctly, models such as llama and stable diffusion, are all types of Artificial Neural Networks (ANNs). ...
timhc22's user avatar
  • 101
1 vote
0 answers
106 views

How speed up pytorch model loading time

I have deployed the background removal model( Pytorch- pre-trained u2net) in aws using lambda and EFS file system and APIgetway. I have stored my model in efs and loading to the lambda. the model is ...
suri's user avatar
  • 11
1 vote
1 answer
154 views

Alternative to EC2 for running ML batch training jobs on AWS

We are building an ML pipeline on AWS, which will obviously require some heavy-compute components including preprocessing and batch training. Most the the pipeline is on Lambda, but Lambda is known to ...
Cybernetic's user avatar
1 vote
1 answer
93 views

Deploying ML/Deep Learning on AWS Lambda for Long-Running Training, not just Inference

Serverless technology can be used to deploy ML models to production, since the deployment package sizes can be compressed if too large (or built from source with unneeded dependencies stripped). But ...
Cybernetic's user avatar
4 votes
2 answers
5k views

sklearn and pandas in AWS Lambda

I made a front end where I would like to make REST calls to an AWS Lambda interfaced with AWS API Gateway. I dumped my model as a pickle file (and so my encoders) which I initially trained locally. ...
3nomis's user avatar
  • 541