Anas Nassar, Steve Mohr, Leonard Apanasevich, Himanshu Sharma. STREAM: Multi-Tier LLM Inference Middleware with Dual-Channel HPC Token Streaming. In Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities, Minneapolis, MN, USA, July 26-30, 2026. ACM, 2026. [doi]
Abstract is missing.