Kimi Developers(@KimiDevs):Agent workloads bring long contexts, bursty traffic, and frequent tool calls, creating new demands for AI serving. Together with @AMD , we rebuilt the stack for Kimi K2.6 on AMD Instinct™ MI355X, with scheduler-aware multi-tier KV caching. Up to 3.2× smaller p99 TTFT and 7.7% higher total-token throughput, with no accuracy tax. Happy to see more Kimi running on AMD chips! Tech blog:

Kimi Developers

@KimiDevs

The official Kimi account for developers building with Kimi Code and the Kimi API.

加入 May 2026

4 正在關注 69.7K 粉絲

Kimi Developers@KimiDevs

2026.07.22 14:00

Agent workloads bring long contexts, bursty traffic, and frequent tool calls, creating new demands for AI serving. Together with @AMD , we rebuilt the stack for Kimi K2.6 on AMD Instinct™ MI355X, with scheduler-aware multi-tier KV caching. Up to 3.2× smaller p99 TTFT and 7.7% higher total-token throughput, with no accuracy tax. Happy to see more Kimi running on AMD chips! Tech blog: