Popular repositories Loading

1. dgx-spark-deepseek-v4-flash dgx-spark-deepseek-v4-flash Public

   2x DGX Spark (GB10) running DeepSeek-V4-Flash: dual-node FP8 TP=2 (~41 tok/s single / ~350 agg), single-node ds4, a 10-model GGUF benchmark suite, and a cross-machine comparison (Mac M2 Ultra, RTX …

   Python 10 1

2. blackwell-llm-toolkit blackwell-llm-toolkit Public

   Empirical recipes, configs, and benchmarks for running modern open-weight LLMs on NVIDIA Blackwell GPUs (RTX PRO 6000, RTX 50-series). NVFP4 + TensorRT-LLM + vLLM + llama.cpp + LMCache, all verifie…

   Shell 6

3. ComfyUI-TeaCache ComfyUI-TeaCache Public

   Forked from welltop-cn/ComfyUI-TeaCache

   making a working version for my own use & others use

   Python 2

4. blackwell-16gb-llm-starter blackwell-16gb-llm-starter Public

   Tested setup, configs, and benchmarks for local LLM inference on 16 GB NVIDIA Blackwell GPUs.

   Shell 2

5. blockbuster blockbuster Public

   Rent cloud GPUs. Make movies. Interactive CLI for ComfyUI on cloud GPUs.

   Python 1

6. phonegap phonegap Public