Popular repositories Loading
-
kindling-spark-os
kindling-spark-os PublicMinimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes
-
glm-5.3-flash-gx10
glm-5.3-flash-gx10 PublicGLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.
-
-
glm-5.3-flash-exlr8-gx10
glm-5.3-flash-exlr8-gx10 PublicGLM-5.3-Flash exlr8 (EXL3-trellis experts) serving recipe for GB10: vLLM + mentat, TP=1/2/3/4, exlr8 MoE kernels
Repositories
- gr8 Public
A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash
- glm-5.3-flash-exlr8-2x-spark Public
GLM-5.3-Flash exlr8 on two GB10 Sparks (TP=2) with gr8: K4, int4 KV, DFlash2, on-disk prompt cache
- deepseek-v4.1-flash-exlr8-4x-spark Public
DeepSeek-V4.1-Flash exlr8 on four GB10 Sparks (TP=4) with gr8: fp8 KV, Engram, 32 chats at once, fast mode by default
- glm-5.3-exlr8-5x-spark Public
GLM-5.3 EXLR8 on five DGX Sparks (T5X, 737K context) — launch recipe for kindlingai/gr8
- glm-5.3-exlr8-6x-spark Public
GLM-5.3 EXLR8 on six DGX Sparks (K3, 1M context) — launch recipe for kindlingai/gr8
Most used topics
Loading…