Popular repositories Loading

1. DeepSeek-v4-Flash-Vision-Exp-DSpark-1M-NVFP4-KV-2x-DGX-Spark DeepSeek-v4-Flash-Vision-Exp-DSpark-1M-NVFP4-KV-2x-DGX-Spark Public

   DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark

   Python 475 59

2. GLM-5.3-Flash-NVFP4-DFlash2-2x-DGX-Spark GLM-5.3-Flash-NVFP4-DFlash2-2x-DGX-Spark Public

   GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patched sm121 image, probes and full report.

   Python 158 19

3. Deepseek-v4-Flash-TP2-DGX-Spark-500k-CTX Deepseek-v4-Flash-TP2-DGX-Spark-500k-CTX Public

   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 gotchas.

   Shell 81 12

4. GLM-5.2-QuantTrio-200K-4x-DGX-Spark--36tok-s GLM-5.2-QuantTrio-200K-4x-DGX-Spark--36tok-s Public

   Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster

   Python 77 9

5. Qwen3.8-Flash-Next-NVFP4-DGX-Spark Qwen3.8-Flash-Next-NVFP4-DGX-Spark Public

   Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-vocab MTP draft; TP2 SPEED 53.7; TP4 CONTEXT 9M KV pool. Lau...

   Python 76 10

6. MiniMax-M3-2x-DGX-Spark-36-tok-s MiniMax-M3-2x-DGX-Spark-36-tok-s Public

   MiniMax-M3 (428B, no pruning) at 36 tok/s on ×ばつ NVIDIA DGX Spark — W4A16 GPTQ + NVFP4 KV + EAGLE-3 speculative decoding on vLLM. Three serving lanes: speed / balanced / long-context.

   46 4