Hao AI Lab 开源 DJev-serve 推理引擎
Every move is one forward pass of DJev on DiffusionGemma, zero tokens generated. Our open-source engine, DJev-serve, runs each decision as one CUDA graph on NVI
AI 导读
每一步都是 DJev 在 DiffusionGemma 上的一次前向传播，零 token 生成。我们的开源引擎 DJev-serve 在 NVIDIA GB200 NVL72 和 B200 上，把每个决策作为一张 CUDA graph 运行。
正文
当前显示原文，中文全文译文尚未就绪。
Every move is one forward pass of DJev on DiffusionGemma, zero tokens generated. Our open-source engine, DJev-serve, runs each decision as one CUDA graph on NVIDIA GB200 NVL72 and B200. https://t.co/fjJt1EzY4Q