Show HN: KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill
https://github.com/kvcache-ai/ktransformers
Hey Hacker News! We are excited to share the new version of KTransformers, a flexible framework designed for cutting-edge LLM inference optimizations! Leveraging state-of-the-art kernels from llamafile and marlin, KTransformers seamlessly enhances the performance of HuggingFace Transformers, making it possible to operate large 671B MoE models or extremely long 1M context locally with promising...