Popular repositories Loading

1. qwen3.8-flash-next-dgx-spark-sglang qwen3.8-flash-next-dgx-spark-sglang Public

   Production recipe for serving Qwen3.8-Flash-Next (180B Hybrid MoE) on a single 128GB NVIDIA DGX Spark with SGLang, NVMe PLE offloading & MTP speculative decoding.

   Jinja 9

2. glm-5.3-flash-dgx-spark-dflash2 glm-5.3-flash-dgx-spark-dflash2 Public

   A practical recipe for serving GLM-5.3-Flash (320B MoE) on a single 128GB NVIDIA DGX Spark with DFlash2 speculative decoding.

   Shell 5