AWS Neuron implementation for Inf1 and Inf2 chips -- 2
Budget: $30 – $250 USD
I am looking for someone with expertise in AWS technologies to help me implement AWS Neuron on my Inf1 and Inf2 chips. Specifically, I need assistance with setting up the product processors to do the implementation using an existing codebase.
You must be able to use Pytorch and AWS Neuron and combine existing models from Huggingface with some custom logic. In the end we should have a highly performant running model on an Inferentia1 chip for which we can expose a public endpoint.
Specifically, we need the following
1. You will get the model that should be made running on Inf1
2. You make it running
3. You provide me with the scripts, such that I can create an Inf1 instance (Sagemaker or EC2).
4. You provide me with the scripts to run it on the Sagemaker resp. EC2 instance. (Reproduction of your).
5. You provide with some code to deploy it on Sagemaker.
6. You provide with some code to containerize the ML model plus to run it on an Inf1 instance.
Please be aware that we will only consider those candidates that did not just spam here.
You must be able to use Pytorch and AWS Neuron and combine existing models from Huggingface with some custom logic. In the end we should have a highly performant running model on an Inferentia1 chip for which we can expose a public endpoint.
Specifically, we need the following
1. You will get the model that should be made running on Inf1
2. You make it running
3. You provide me with the scripts, such that I can create an Inf1 instance (Sagemaker or EC2).
4. You provide me with the scripts to run it on the Sagemaker resp. EC2 instance. (Reproduction of your).
5. You provide with some code to deploy it on Sagemaker.
6. You provide with some code to containerize the ML model plus to run it on an Inf1 instance.
Please be aware that we will only consider those candidates that did not just spam here.