Questions tagged with AWS Neuron
Content language: English
Select up to 5 tags to filter
Sort by most recent
Browse through the questions and answers listed below or filter and sort to narrow down your results.
Please, guide me how to install neuron runtime on ubuntu 22.04?
I always get cannot locate collectives after running this
"sudo apt-get install aws-neuronx-collectives=2.* -y"
I have WSL Ubuntu...
0
answers
0
votes
196
views
asked 10 days agolg...
Hello, i'm using **pytorch-inference:2.0.1-gpu-py310-cu118-ubuntu20.04-sagemaker** AMI and following this guide...
1
answers
0
votes
543
views
asked 8 months agolg...
hello,
i'm using **pytorch-inference:2.0.1-gpu-py310-cu118-ubuntu20.04-sagemaker** image to run the service i'd like to switch to INF2 instance.
~~I think i can try to use...
1
answers
0
votes
604
views
asked 9 months agolg...
Hi,
One big difference I've noticed between the inf1 and inf2 development experience is that with inf2, we are not able to compile models outside of inf2 instances (unlike inf1 where we were able to...
2
answers
0
votes
286
views
asked 9 months agolg...
Which version of torch_neuronx is used in the example?
This is asked because neither the API Reference at [aws...
2
answers
0
votes
321
views
asked 10 months agolg...
I am trying to run inference of GPT2 on inf2 instance using this transformers-neuronx example:
[https://github.com/aws-neuron/transformers-neuronx#hugging-face-generate-api-support]()
I keep getting...
1
answers
0
votes
311
views
asked a year agolg...
I am currently facing an issue with the AWS Neuron SDK when trying to run the PyTorch example provided in the AWS Neuron GitHub repository on a Deep Learning AMI Neuron PyTorch 1.13 (Ubuntu 20.04)...
1
answers
0
votes
518
views
asked a year agolg...
Pytorch 2.0.1 is backward compatible so it shall be fine to use it but when we tried to we got this error.
ImportError
Invalid dependency version torch==2.0.1+cu117. Expected torch==1.13.1
```
#...
1
answers
0
votes
497
views
asked a year agolg...
The audio going into the model would be different lengths, and I saw a post saying "At the time of writing, the AWS Neuron SDK does not support dynamic shapes, which means that the input size needs to...
1
answers
0
votes
274
views
asked a year agolg...
Hi,
I am trying to deploy the Databricks open source LLM i.e Dolly on inf2 instance. Instance type is `inf2.24xlarge` used the AMI `Deep Learning AMI Neuron PyTorch 1.13 (Ubuntu 20.04) 2023051`.
I am...
2
answers
0
votes
768
views
asked a year agolg...
Hi,
I have some code which generates a shape of torch.Size([1, 512, 1024] when calling bert on inf1.
I have compiled the model for inf2.
However the same code on inf2 produces a shape of...
1
answers
0
votes
338
views
asked a year agolg...
Hi, I'm trying to run the gptj_demo on Inf2 with AMI Deep Learning AMI Neuron PyTorch 1.13.0 (Ubuntu 20.04) 20230405 and installed the pytorch neuron as...
1
answers
0
votes
446
views
asked a year agolg...