Skip to content

Allow for multiple Inferentia ASICs to be assigned to each API replica #1123

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
RobertLucian opened this issue Jun 13, 2020 · 1 comment · Fixed by #2304
Closed

Allow for multiple Inferentia ASICs to be assigned to each API replica #1123

RobertLucian opened this issue Jun 13, 2020 · 1 comment · Fixed by #2304
Labels
refactor Improve code quality
Milestone
v0.38

Comments

@RobertLucian
Copy link
Member

Description

Remove the current limitation of 1 Inferentia ASIC per API replica. We're currently forced to go with only one because of some issue in the Neuron RTD.

Motivation

It will allow to partition models across multiple Inferentia ASICs.

Additional context

As reported in aws-neuron/aws-neuron-sdk#110.
@RobertLucian RobertLucian added refactor Improve code quality blocked Blocked on another task or external event labels Jun 13, 2020
@deliahu deliahu removed the blocked Blocked on another task or external event label Aug 14, 2020
@RobertLucian
Copy link
Member Author

This is now possible thanks to https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-container-tools/k8s-neuron-scheduler.md.

@deliahu deliahu mentioned this issue Jul 1, 2021
Merged
@deliahu deliahu added this to the v0.38 milestone Jul 5, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
refactor Improve code quality
Projects
None yet
Milestone
v0.38
Development

Successfully merging a pull request may close this issue.

Update versions cortexlabs/cortex
2 participants
@deliahu @RobertLucian