Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Can Anyone Recommend Some Good Ai Deployment Frameworks For Kubernetes? (Better If They Have/Can Be Integrated With Clearml)

Can anyone recommend some good AI deployment frameworks for kubernetes? (better if they have/can be integrated with ClearML)

  
  
Posted 3 years ago
Votes Newest

Answers 9


Let me know if I understand you correctly, the main goal is to control the model serving, and deploy to your K8s cluster, is that correct ?

  
  
Posted 3 years ago

So good news (1) Dashboard is being worked on as we speak. (2) we released clearml-serving doing exactly that, the next release of clearml-serving will include integration with kfserving (under the hood) essentially managing the serving endpoints on top of the k8s cluster , wdyt?

  
  
Posted 3 years ago

I want to find a good deployment framework (if exists) and integrate it into our ClearML workflow).
like get latest release with prod tag from clearml api and apply that to k8s.
something along those lines

  
  
Posted 3 years ago

BTW: if you feel like pushing forward with integration I'll be more than happy to help PRing new capabilities, even before the "official" release

  
  
Posted 3 years ago

oh great!
let me take a look at this. There’s a lot of custom tooling so integration is very important.

cc: FiercePenguin76 ^^^

  
  
Posted 3 years ago

Hi DisgustedDove53
When you say "deployment" there are a lot of way to interpret that 🙂 what exactly are you looking for ?

  
  
Posted 3 years ago

Yes.
ClearML has all these awesome dashboards. I was thinking maybe there will be some deploy to prod/staging/shadow button so you can do everything from there. (Like Gitlab CI/CD if you have seen that)
That would be ideal.

  
  
Posted 3 years ago

Hi AgitatedDove14

For example version control, A/B testing, shadow testing, rollback etc..
We can use conventional solutions that we already use. Like Helm and Istio.

But for example is there any tools that gives more insight into model performance in production? or gives more knobs and settings specific for AI.
using common microservice deployment frameworks will be limiting.

I found some solutions (KubeFlow, Seldon Core, http://run.ai , MLFlow, …) but haven’t got to look at them really.

  
  
Posted 3 years ago
1K Views
9 Answers
3 years ago
one year ago
Tags