Cortex
AI
model serving
SHOW HN2020
65points
19comments
#913of 3,028 in 2020
Top 31%of 2020 by points
How HN took it
LovedMost comments that take a side are positive
4 positive, 6 neutral or asking, 0 mixed, 0 critical, out of 10 comments about the project. Thread score +0.22.
Idea: 1 for, 0 againstExecution: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Cleaner and cheaper alternative to SageMaker
From 2 comments
This certainly looks like a cleaner way to deploy an ML model than SageMaker. Couple of questions: * Is this really for more intensive model inference applications that need a…
itsderek23 on HNIn general, Cortex will be significantly cheaper because you're only paying AWS for EC2 (the bulk of the bill) and the other AWS services used (a much smaller portion of the…
calebkaiser on HN
Inspired other projects such as chantilly
From 1 comment
Hey there, great work. I used Cortex as an inspiration when designing chantilly: https://github.com/creme-ml/chantilly, which is a much less ambitious solution tailored towards…
Lemaxoxo on HN
Objections
Likely overkill for small models that do not need a cluster
From 2 comments
This certainly looks like a cleaner way to deploy an ML model than SageMaker. Couple of questions: * Is this really for more intensive model inference applications that need a…
itsderek23 on HNYou're 100% right that Cortex is designed for the production use-case. A lot of our users are running Cortex for "small" production use cases, since the Cortex cluster can…
calebkaiser on HN
Lacks built-in API authentication; users need AWS API Gateway
From 1 comment
Right now, users handle API auth by using AWS API gateway in front of Cortex, but incorporating AWS API Gateway into Cortex to automate this is on our short term roadmap.
calebkaiser on HN
Requests
Managed service offering
From 1 comment
Is it possible to partner with you to offer a managed service for Cortex? We are looking at your solution to offer our clients for deployment.
cgoltsev on HN
Built-in API Gateway integration for authentication
From 1 comment
Right now, users handle API auth by using AWS API gateway in front of Cortex, but incorporating AWS API Gateway into Cortex to automate this is on our short term roadmap.
calebkaiser on HN
Tighter version control integration
From 2 comments
This certainly looks like a cleaner way to deploy an ML model than SageMaker. Couple of questions: * Is this really for more intensive model inference applications that need a…
itsderek23 on HNYou're 100% right that Cortex is designed for the production use-case. A lot of our users are running Cortex for "small" production use cases, since the Cortex cluster can…
calebkaiser on HN
Questions
Is it suitable for small models without a cluster?
From 1 comment
This certainly looks like a cleaner way to deploy an ML model than SageMaker. Couple of questions: * Is this really for more intensive model inference applications that need a…
itsderek23 on HN
Can it be run cheaply for a side project?
From 1 comment
One of the things that has deterred me from SageMaker is how expensive it can be for a side project. Real-time endpoints start at $40-$50 per month, which would be a bit too much…
dodata on HN
How does it compare to Lambda and Kubeflow?
From 2 comments
Why would I use this over deploying the model to a lambda function aside from lack of GPU? (not trying to be confrontational, genuinely don't know) Won't lambda functions scale…
cameronfraser on HNHow is this compared to KubeFlow?
_____smurf_____ on HN
Alternatives named
SageMaker
From 2 comments
This certainly looks like a cleaner way to deploy an ML model than SageMaker. Couple of questions: * Is this really for more intensive model inference applications that need a…
itsderek23 on HNOne of the things that has deterred me from SageMaker is how expensive it can be for a side project. Real-time endpoints start at $40-$50 per month, which would be a bit too much…
dodata on HN
Kubeflow
From 1 comment
How is this compared to KubeFlow?
_____smurf_____ on HN
AWS Lambda
From 1 comment
Why would I use this over deploying the model to a lambda function aside from lack of GPU? (not trying to be confrontational, genuinely don't know) Won't lambda functions scale…
cameronfraser on HN
Docker
From 1 comment
Has anyone used Cortex in production? - Could you share your experiences? - why would one choose this over docker for instance?
bobosha on HN