Popular repositories Loading

1. spark-bench spark-bench Public

   Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics

   HTML 136 10

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

   DeepSeek V4 Flash DSpark on 2x DGX Spark — NVFP4 KV cache, 1M context, speculative decoding. Based on MiaAI-Lab dual-Spark packaging.

   Python 6

3. qwen-sglang-dgx-spark qwen-sglang-dgx-spark Public

   Deploy Qwen3.6-35B on a DGX Spark (GB10) with SGLang v0.5.15 for long-context multi-agent serving. Includes a reproducible SGLang-vs-vLLM comparison.

   Shell 1

4. Laguna-S-2.1-NVFP4-1x-DGX-Spark Laguna-S-2.1-NVFP4-1x-DGX-Spark Public

   poolside Laguna S-2.1 (118B/8B MoE) on ONE NVIDIA DGX Spark - validated NVFP4 recipe + day-0 benchmark: TrueScore 86.5, agentic 99.3, 19 tok/s single / 84 tok/s @ c8. Needs vLLM >= 0.25 (older stac…

   1

5. specserve specserve Public

   Lightweight web GUI for managing vLLM model serving with speculative decoding

   Python

6. Qwopus3.6-27B-Q4_K_M-DGX-Spark Qwopus3.6-27B-Q4_K_M-DGX-Spark Public

   Qwopus 27B (Q4_K_M) on NVIDIA DGX Spark (GB10) via llama.cpp — MTP speculative decoding, 49-scenario TrueScore benchmark

   Shell