Welcome to AIBrix blogs

AIBrix is a open source cost-efficient, scalable and pluggable Infrastructure for GenAI applications.

AIBrix ModelClaim: Engine-Aware GPU Sharing for Long-Tail Models

AIBrix v0.8.0 Release: Building a More Dynamic Inference Platform

Should You Self-Host Batch Inference? An Honest Cost Breakdown

AIBrix KVCache: Optimizing Single-Node P/D Disaggregation

AIBrix v0.7.0 Release: Management Console, Self-Hosted Batch, KV-Centric Disaggregation, and a Highly-Available Gateway

AIBrix v0.6.0 Release: Envoy Sidecar, Mixed LLM Workloads Routing, Routing Profiles, LoRA Delivery & New APIs

PrisKV: A Colocated Tiered KVCache Store for LLM Serving

AIBrix v0.5.0 Release: Batch API, KVCache v1 Connector, and Enhanced P/D orchestration

AIBrix v0.4.0 Release: P/D Disaggregation and Expert Parallelism Support, KVCache v1 Connector, KV Event Synchronization & Multi‑Engine Support

AIBrix v0.3.0 Release: KVCache Offloading, Prefix Cache, Fairness Routing, and Benchmarking Tools