Article:Elite Test Engineering
Serving DeepSeek V4 Flash on Dual DGX Spark Nodes
A detailed technical setup report documents serving DeepSeek-V4-Flash (284B MoE) across two DGX Spark nodes powered by Grace Blackwell chips using Ray and vLLM. It highlights workarounds for unified memory monitoring, NCCL RDMA deadlocks, and CUDA graph issues, as well as a 45% speedup using native speculative decoding.
From Video: Testing DeepSeek V4 Flash on a Clustered DGX Spark and Acer GN100