Из ленты dev.to devops — кратко, чтобы не потерять.
What: AMD shipped ATOM + ATOMesh , a ROCm-native LLM serving stack whose headline trick is prefill/decode disaggregation — splitting the two phases of inference onto separate pools of GPUs instead of crowding them onto one. Why: Prefill and decode have opposite bottlenecks — prefill is compute-bound, decode is memory-bandwidth-bound — so running them on the same worker wastes hardware and lets one long prompt stall everyone else’s token stream . vs prior: A co-located server (vanilla single-pool vLLM) interleaves prefill and decode on the same GPUs; disaggregation runs each on its own pool tuned for its bottleneck, paying for it by shipping the KV cache across the interconnect between them. Think of it as A restaurant kitchen that splits the prep station from the plating line. ORDER (the p
Полный текст и контекст у первоисточника: https://dev.to/pueding/amd-atom-atomesh-prefilldecode-disaggregation-on-rocm-2p0a