GitHub - tonyd2wild/deepseek-v4-flash-dgx-spark: Working recipe to serve DeepSeek-V4-Flash across...
Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — Docker image, launch scripts, RDMA/NCCL setup, and the gotch...
github.com