GPTProto

Blog MiniMax-H3 on 8×H200: 1.95× Lossless, Up to 6.24× at 0.76–0.91 SSIM We benchmarked MiniMax-H3 video generation on 8× NVIDIA H200 with SGLang Diffusion, holding prompts, seeds, resolution, frame rate, and denoising steps fixed across six workloads. - SGLang's dense, l... SGLang Diffusion Team, Cache-DiT Team, NVIDIA, Ant Group

LMSYS:Blog(Chatbot Arena 团队)··Research Papers

SGLang Diffusion 团队在 8×NVIDIA H200 上对 MiniMax-H3 视频生成进行基准测试,其密集无损路径较 Diffusers 快 1.85–1.95×,无近似损失。