Comments (2)
njhill
commented on August 25, 2024
Hi @Phelan164, the short answer is in theory yes (Model-mesh actually started out independently of Kubernetes), but it would require a fair amount of custom setup/configuration, especially if you want to use the built-in model server integration that we have as part of the wider modelmesh-serving framework.
I would strongly recommend using it on Kube via the controller (following quickstart here). You can install local/lightweight Kubernetes clusters using something like minikube or kind.
from modelmesh.
Phelan164
commented on August 25, 2024
@njhill thanks for your suggestion.
Yes, I could work with modelmesh via controller and deploy into kubenetes cluster.
But just want to make very simple development env, so I want to setup modelmesh run in docker and directly interact with that via gRPC.
Related to "custom setup/configuration", could you share some basic guidelines ?
Thanks so much for your support
from modelmesh.
Related Issues (20)
- Log reason for unready model mesh container HOT 2
- How to run modelmesh without k8s HOT 1
- Is it possible to log the actual payload data instead of just the number of bytes?
- Incorrect limits in dockerfile when cgroup v2 is used HOT 1
- Model per instance model-mesh by default HOT 1
- Questions about functioning of ModelMesh HOT 9
- rewrite modelmesh from java to golang HOT 1
- Support individual model metrics HOT 3
- Error when enabling TLS for ModelMesh HOT 5
- “Nowhere available to load” error in inference response HOT 4
- fq_names boolean metrics sub-parameter is inverted HOT 1
- OOMKilled Error HOT 2
- ModelMesh serving not working with Kserve Client APIs HOT 1
- Add documentation related to "standalone" use of modelmesh container
- ModelMesh model-loading decision process HOT 10
- Include the resolved model Id in Payloads HOT 1
- Document design decisions for decentralized scaling and share performance evaluation HOT 1
- how about using modelmesh to serve thousands of stable diffusion models HOT 2
- ByteBuf leak observed in production deployment HOT 6
- inference with timeouts leads to Internal error HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from modelmesh.