Picom-code/pico-dgx-ds4
DeepSeek V4.1 Flash on 4x DGX Spark: 90/144 tok/s chat/code single-user, 376 tok/s at 16 distinct users, 1M context, images. Fork of blaesus/dsgx10.
GitHub repository with 112 stars and 19 forks.
Language: Cuda
Topics: cuda, deepseek, dgx-spark, inference-engine, llm-inference, local-llm, multi-node, openai-api, rdma, roce