ExLlamaV3 recipe for Flash-Next on a DGX Spark

Step-by-step recipe to squeeze the 125B model onto one DGX Spark instead of two, with config and measured throughput.

Follow-up engine that speeds single-Spark decoding of the 125B model via a custom tensor layout.

Early write-up of how to serve the model on a single DGX Spark, published within a day of the weights landing.

Dual-node vLLM deployment of the NVFP4 build across a pair of DGX Sparks, for higher context and throughput.