2026-11-11 · America/Los_Angeles · 社区动态 · #10

1/ We set Maxwell to optimize DeepSeek-V4.1-Flash serving on B200s.

1/ We set Maxwell to optimize DeepSeek-V4.1-Flash serving on B200s. Maxwell’s engine outputs 3x more tokens per GPU than vLLM at the same speed per user, or serves 2x speed per user for typical loads. It beats every published B200 setup, and is even faster than all comparable https://t.co/SQIDpBzZk0

阅读原文查看评分、趋势与关联来源阅读整期日报

热度 40.5 / 100；排名与评分保留该期记录。