Scaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentX
Scaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentX
摘要
Inside the Kimi K3 optimization effort: understanding the bottlenecks and the decisions that made inference faster
Inside the Kimi K3 optimization effort: understanding the bottlenecks and the decisions that made inference faster
译自 vLLM · 官方博客 · 录于 二〇二六年十月十六日