gx10

1 个项目 · ⭐ 13

lrozewicz/vLLM-Moet-GB10

Run DeepSeek-V4-Flash 304B on a single NVIDIA GB10 / DGX Spark - 2-bit MoE planes, FP4 quality recovery, speculative decoding

Sass ⭐ 13 ⑂ 3 Apache-2.0 · 13 天前推送

deepseek llm-inference

13 天前