Serving DeepSeek-V4.1-Flash (552B MoE) across four NVIDIA DGX Sparks with TensorFold and vLLM, with launch scripts, patches and measured results.
1190PythonMIT更新 12 時間前
#tensor-parallel
tensor-parallel に関連する厳選 GitHub リポジトリ。AI による概要と主要な指標を掲載しています。
Serving DeepSeek-V4.1-Flash (552B MoE) across four NVIDIA DGX Sparks with TensorFold and vLLM, with launch scripts, patches and measured results.