[Feature] Implement "Miles Diffusion Router" for Workload-Aware Rollouts

Motivation

To support large-scale RL rollouts and high-throughput generation, we need to implement a dedicated router for the diffusion engine, tentatively named Diffusion Router.

This router will build upon the concepts of Cache-Aware Load Balancing and Data Parallel (DP) Routing used in the SGLang LLM engine. The goal is to implement a "workload-minimal" routing strategy that ensures requests are distributed to the most available or appropriate engine instances while maintaining system health.

Goals

1. Core Infrastructure: Create a standalone demo/implementation of a router tailored for sglang-diffusion instances.
2. Interface Support: Implement the following three critical API interfaces:

• health_check: Monitor the status of downstream diffusion workers.
• generate: Route generation requests based on current workload/availability.
• update_weights_from_disk: Interface placeholder (can be a stub for now) to support future dynamic weight updates.

3. Minimalist Routing: Focus on low-latency, workload-aware distribution to minimize generation bottlenecks during rollouts.

Technical Tasks

• Study the existing SGLang Router implementation for LLMs (see resources below).
• Develop the miles-diffusion-router script/module.
• Implement basic load balancing logic (e.g., Least-Request or Round-Robin as a baseline, moving toward workload-minimal).
• Create a demo script showing the router coordinating multiple sglang-diffusion backends.
• Document the setup process and API usage.

Resources

• Concept: [SGLang v0.4 Cache-Aware Load Balancer](https://lmsys.org/blog/2024-12-04-sglang-v0-4/#cache-aware-load-balancer)
• Reference Implementation: [SGLang Router Documentation & Source](https://github.com/sgl-project/sglang/blob/b6e0cfb5e1c355f9526defdf9bbee430c0bfebaa/docs/router/router.md)

Calling community members interested in distributed systems and RL infrastructure! Help us build the backbone of the Miles rollout system.