Kimi says MI355X serving changes cut p99 TTFT by 3.2× and lift throughput 7.7%
AnushElangovan · x · 2026-07-23
Kimi and AMD say they rebuilt the serving stack for Kimi K2.6 on AMD Instinct MI355X, targeting agent workloads with long contexts, bursty traffic, and frequent tool calls.
The update adds scheduler-aware multi-tier KV caching and claims up to 3.2× lower p99 TTFT plus 7.7% higher total-token throughput, with no accuracy loss. The post points readers to the technical blog for details.
More from Infra
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- 80% of the DIY LLM inference hype posters have already quit — it's brutally hard systems work — abhijithneil · 2026-09-11
- Hugging Face's Ultra Scale Playbook: a free book on training LLMs on GPU clusters — mdancho84 · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- LLM Serving Metrics Thread: Why TPOT and Uptime Make or Break User Experience — abhijithneil · 2026-09-11
- PlanetScale launches sharded Postgres: 768 servers acting as one, 1PB scale — dhruv2038 · 2026-09-11