SemiAnalysis@SemiAnalysis_

2026-07-12 01:01·33分钟前

AI 摘要

警报：在 vLLM Kimi（与 xAI 的 Cursor Composer 2.5 采用相同模型架构）上，NVIDIA 碾压 AMD。同时很高兴看到 B300 比 B200 更快。

ALERT： On vLLM Kimi， which has the same model architecture as xAI's Cursor Composer 2.5， NVIDIA mogs AMD. Also great to see B300 faster than B200.

SemiAnalysis@SemiAnalysis_ · X

2026-07-12 01:01·33分钟前

AI 摘要

警报：在 vLLM Kimi（与 xAI 的 Cursor Composer 2.5 采用相同模型架构）上，NVIDIA 碾压 AMD。同时很高兴看到 B300 比 B200 更快。

ALERT： On vLLM Kimi， which has the same model architecture as xAI's Cursor Composer 2.5， NVIDIA mogs AMD. Also great to see B300 faster than B200.