Kindling AI

Popular repositories Loading

1. glm-5.3-flash-gx10 glm-5.3-flash-gx10 Public

   GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.

   Python 92 13

2. kindling-spark-os kindling-spark-os Public

   Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes

   Shell 92 6

3. gr8 gr8 Public

   GLM-5.3 (full) on 3-6 DGX Sparks (GB10): a from-scratch CUDA inference engine

   Cuda 41 9

4. exlr8 exlr8 Public

   EXLR8: a DGX Spark tuned quantization format

   HTML 14 1

5. glm-5.3-flash-exlr8-gx10 glm-5.3-flash-exlr8-gx10 Public

   GLM-5.3-Flash exlr8 (EXL3-trellis experts) serving recipe for GB10: vLLM + mentat, TP=1/2/3/4, exlr8 MoE kernels

   Python 14 1

6. mentat mentat Public

   A very-low-resource API-compatible replacement for Ray

   Rust 11