🌐 BGP - Velocifyer · Scour

GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs 🕸️Network Topology

labiium/routiium: A self-hosted LLM reverse proxy that adds managed auth, multi-provider routing, rate limiting, llm as judge, historyand cost tracking to any OpenAI-compatible 🔗Tailscale

github.com·4d·Hacker News

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing 🖥️Modern CPU

Why I Built a Self-Hosted Alternative to Helicone (and What I Learned) 🏠Self-Hosting

github.com·3d·DEV

MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings 🌐DNS over QUIC

RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization ⚙️Compression Benchmarking

katanemo/plano 0.4.22 🖥️Wayland

Design Insights into Partition Placement and Routing for DNN Inference in Multi-Hop Edge Networks 🕸️Network Topology

I built a manifest standard for agent-callable CLI tools – 93.6% routing accuracy, zero fine-tuning 🐘Mastodon

github.com·4d·DEV

HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models ⚙️Compression Benchmarking

Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways ⚙️Compression Benchmarking

RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment ⚙️Compression Benchmarking

Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression 📶LoRa

RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm 🕸️Network Topology

Log in to enable infinite scrolling