ALL INTELLIGENCE
vLLM 官方博客T1·Infra

Kimi K3 on AMD MI355X Matches NVIDIA B300 Throughput per GPU via AgentX Optimization

By AMD and Embedded LLMOriginal title: Scaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentX
42AI Score

Moonshot AI revealed that Kimi K3 achieves per-GPU throughput parity with NVIDIA HGX B300 on AMD Instinct MI355X accelerators using the AgentX framework. The report details bottleneck analysis and optimization decisions, demonstrating the viability of non-NVIDIA hardware for high-performance LLM inference.

Full Report

Inside the Kimi K3 optimization effort: understanding the bottlenecks and the decisions that made inference faster