Synapse Open Synapse
Tech

Serving GLM-5.3 at 607.8 tok/s across two Nvidia DGX stations with vLLM

HN · · 17 min read

Running a frontier-scale model locally means keeping all its weights in GPU memory; the largest models no longer fit on one machine. Two NVIDIA DGX Stations connected over ConnectX-8 RDMA serve one…

Same story elsewhere

Latest from HN