christopherowen/spark3-vllm-ds41f
Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node DGX Spark fabric.
Repositories
christopherowen/dgx-spark-fan-control
Userland fan control for NVIDIA DGX Spark, with additive RPM floors, a temperature-based curve, Secure Boot signing, and DKMS support.
christopherowen/dgx-spark-power-control
Power telemetry and NVIDIA-bounded power limits for NVIDIA DGX Spark, via the firmware's SPBM page, with Secure Boot signing and DKMS support.
christopherowen/SASSquatch
christopherowen/spark-vllm-mxfp4-docker
christopherowen/codexUI
🚀 Run Codex App UI Anywhere: Linux, Windows, or Termux on Android 🚀
christopherowen/ThunderKittens
Tile primitives for speedy kernels
christopherowen/spark-vllm-docker
Docker configuration for running VLLM on dual DGX Sparks
christopherowen/llama-benchy
llama-benchy - llama-bench style benchmarking tool for all backends
christopherowen/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra
christopherowen/flashinfer
FlashInfer: Kernel Library for LLM Serving
christopherowen/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs