Comments (5)
Possible solution:
- add a
Router()
on the Python side - append the related workers to the
Router
- register the
Router
with the related endpoint (by default will use/inference
)
Problems:
- if a worker belongs to multiple routers, how to reuse it?
from mosec.
\assign
from mosec.
if a worker belongs to multiple routers, how to reuse it?
Perhaps we need to register the route info at rust side, so at different stages of different routes, the same worker can be used for overlapping tasks?
from mosec.
if a worker belongs to multiple routers, how to reuse it?
Perhaps we need to register the route info at rust side, so at different stages of different routes, the same worker can be used for overlapping tasks?
That's necessary for the controller to know the route info.
@cutecutecat This might be difficult to be done in one shot. You can do it step by step. Maybe the 1st target is to support the customized HTTP endpoint instead of the default /inference
with the routing concept. Multi-route can be the next one.
from mosec.
if a worker belongs to multiple routers, how to reuse it?
Perhaps we need to register the route info at rust side, so at different stages of different routes, the same worker can be used for overlapping tasks?
That's necessary for the controller to know the route info.
@cutecutecat This might be difficult to be done in one shot. You can do it step by step. Maybe the 1st target is to support the customized HTTP endpoint instead of the default
/inference
with the routing concept. Multi-route can be the next one.
It might be ok to deploy a simple multi-route Server, but Worker
reuse is a bit hard, and need to design at next step.
I think some Graph algorithms is required to calculating shard Workers
.
from mosec.
Related Issues (20)
- feat: add `Content-Type` header in the response
- feat: generate the OpenAPI doc from the typed request annotation
- feat: how to reload like fastapi or flask HOT 1
- feat: support adaptive batching HOT 2
- feat: support iteration level scheduling HOT 1
- feat: add swagger for the openapi
- feat(docs): add advanced user guide for custom mixin
- unload model automatic HOT 3
- feat: support server side response cache HOT 5
- feat: Have a base image
- feat: Migration guide for triton python backend HOT 1
- Is mosec available on windows? HOT 1
- bug: log is not formatted HOT 1
- feat: support for llama(.cpp) HOT 2
- feat: add route-level metrics
- feat: support dynamic configuration for dynamic batching without service restart HOT 1
- bug: Issue running `echo.py`: Thread 'main' panicked at src/main.rs:118:46: local time offset: IndeterminateOffset HOT 4
- bug: 'site-packages/mosec/bin/mosec' not found on macOS M1 HOT 3
- feat: CORS support ? HOT 1
- bug: "request body is too large" when passing numpy array HOT 11
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 mosec.