Skip to main content

vLLM Semantic Router Work Groups 👋

🌍 WG Initialization

We are looking for interests around vLLM Semantic Router project and separate it into different WGs.

Please comment on GitHub Issue #15 if you are interested in one or more.

⛰️ vLLM Semantic Router Community WG

This section is about setting WG around this project, to gather focus on specify areas.

🧠

RouterCore

area/core

Using embedded SLM, implement advanced routing algorithm like classify, security detection, auto reasoning etc.

Skills Needed:

  • Machine learning
  • BERT models
  • Classification algorithms

Current Needs:

  • Model optimization
  • Algorithm improvements
  • Reasoning logic
🔬

Research

area/research

Explore the frontier of SLM (Small Language Model) in vLLM Semantic Router, improving latency and context of SLM.

Skills Needed:

  • Model Training
  • Model Fine-Tuning
  • Deep Learning

Current Needs:

  • SLM research
  • Latency optimization
  • Context improvement
🌐

Networking

area/networking

Envoy ExtProc, Traffic Management, Networks Optimization

Skills Needed:

  • Envoy proxy
  • Network protocols
  • Performance optimization

Current Needs:

  • Load balancing
  • Traffic routing
  • Network security
📈

Observability

area/observability

Metrics collection, distributed tracing, monitoring dashboards, and structured logging for production visibility

Skills Needed:

  • Prometheus/Grafana
  • OpenTelemetry
  • Log aggregation
  • Monitoring systems

Current Needs:

  • Metrics implementation
  • Tracing integration
  • Dashboard creation
  • Log standardization
📊

Bench

area/benchmark

Reasoning Benchmark Framework, Performance Optimization

Skills Needed:

  • Performance testing
  • Benchmarking tools
  • Data analysis

Current Needs:

  • Benchmark frameworks
  • Performance metrics
  • Testing automation
🐳

Environment

area/environment

Docker Compose, Kubernetes, Local support, Cloud Foundry Integration

Skills Needed:

  • Docker
  • Kubernetes
  • Cloud platforms
  • DevOps

Current Needs:

  • Helm charts
  • Deployment automation
  • Cloud integrations
🔧

Test and Release

area/tooling, area/ci

CI/CD, Build, test, release

Skills Needed:

  • CI/CD tools
  • Build automation
  • Release processes

Current Needs:

  • Test automation
  • Release pipelines
  • Quality assurance
👥

User Experience

area/user-experience

User experience across vLLM Semantic Router, API, Configuration and CLI guidelines and support

Skills Needed:

  • API design
  • UX/UI
  • Developer experience

Current Needs:

  • API improvements
  • CLI enhancements
  • User feedback integration
📚

Docs

area/document

User docs, information architecture, infrastructure

Skills Needed:

  • Technical writing
  • Documentation tools
  • User experience design

Current Needs:

  • API documentation
  • Tutorials
  • Deployment guides

🔝 Community Promotion

We are grateful for any contributions, and if you show consistent contributions to the above specify area, you will be promoting as its maintainer after votes from maintainer team, and you will be invited to semantic-router-maintainer group, and granted WRITE access to this repo.

How to Get Involved

  1. Choose Your Interest Area: Review the working groups above and identify which areas align with your skills and interests
  2. Join the Discussion: Comment on GitHub Issue #15 to express your interest
  3. Start Contributing: Look for issues labeled with the corresponding area tags (e.g., area/document, area/core)
  4. Collaborate: Connect with other community members working in the same areas

Contact

For questions about working groups or to get involved: