sudoingX/dgx-spark-deepseek-v41
DeepSeek-V4.1-Flash on two NVIDIA DGX Sparks: EXL3 weights from the official checkpoint, upstream vLLM with our patches and decode kernels
GitHub repository with 18 stars and 0 forks.
Language: Python
Topics: deepseek, dgx-spark, exl3, gb10, quantization, vllm