DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM kit, exact speculative decoding. Work in progress.
Like jayleaton/deepseek-v41-tensorfold-spark, 0 likes 0 Bookmark jayleaton/deepseek-v41-tensorfold-spark, 0 bookmarks 0 DeepSeek-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold
Like MiaAI-Lab/DeepSeek-v4.1-Flash-1017-2x-DGX-Sparks, 0 likes 0 Bookmark MiaAI-Lab/DeepSeek-v4.1-Flash-1017-2x-DGX-Sparks, 0 bookmarks 0 DeepSeek-V4.1-Flash on two NVIDIA DGX Sparks: EXL3 weights from the official checkpoint, upstream vLLM with our patches and decode kernels
Like sudoingX/dgx-spark-deepseek-v41, 0 likes 0 Bookmark sudoingX/dgx-spark-deepseek-v41, 0 bookmarks 0 DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s). Launchers, run records, measured numbers. Older vLLM lanes kept.
Like tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks, 0 likes 0 Bookmark tonyd2wild/DeepSeek-V4.1-Flash-TP2-and-TP4-DGX-Sparks, 0 bookmarks 0 DeepSeek V4 Flash @ 1M token context on 2x NVIDIA DGX Spark — production-tested recipe (45 tok/s decode, real 800K prompts served)
Like tonyd2wild/DeepSeek-V4-Flash-2x-Spark-1M, 0 likes 0 Bookmark tonyd2wild/DeepSeek-V4-Flash-2x-Spark-1M, 0 bookmarks 0 BertholomusAI recipe: DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark (GB10), our own TensorFold TP2 engine. Weights: Mia-AiLab EXL3 2.9bpw (MIT).
Like bertholomus/deepseek-v4.1-tensorfold-tp2-2xgb10, 0 likes 0 Bookmark bertholomus/deepseek-v4.1-tensorfold-tp2-2xgb10, 0 bookmarks 0 DeepSeek-V4.1-Flash on 3-4x NVIDIA DGX Sparks
Like MiaAI-Lab/DeepSeek-v4.1-Flash-DGX-Sparks, 0 likes 0 Bookmark MiaAI-Lab/DeepSeek-v4.1-Flash-DGX-Sparks, 0 bookmarks 0 DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks
Like MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks, 0 likes 0 Bookmark MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks, 0 bookmarks 0 DeepSeek v4 Flash EXL3 on one DGX Spark
Like MiaAI-Lab/DeepSeek-v4-Flash-One-DGX-Spark, 0 likes 0 Bookmark MiaAI-Lab/DeepSeek-v4-Flash-One-DGX-Spark, 0 bookmarks 0