Pinned Loading

1. TandemLLM TandemLLM Public

   Inference engine for Qwen3.8-27B on one DGX Spark: speculative draft trees sized by StairCut, NVFP4 kernels, exact recurrent-state caches

   Python 21

2. inference-atlas inference-atlas Public

   A community-owned map of LLM inference engine configurations — benchmarks, evals and coverage gaps, hosted on GitHub Pages. The repo is the database.

   Python 16 6

3. arbiter arbiter Public

   Serve typed-decision (System 1) models — Laya or your own — on NVIDIA GPUs or Apple Silicon, with a Jev-compatible API and coding-agent integrations

   HTML 33 3

4. qwen38-flash-next-spark qwen38-flash-next-spark Public

   Run Qwen3.8-Flash-Next (180B) on a single DGX Spark by keeping its 51B n-gram embedding table on NVMe

   Shell 125 9

5. deepseek-v41-flash-spark deepseek-v41-flash-spark Public

   DeepSeek-V4.1-Flash on a single DGX Spark (GB10): resident hot experts + NVMe streaming, DSpark, OpenAI API. Work in progress.

   Python 120 13