1
Prefill/Decode-Aware Evaluation of LLM Inference on Emerging AI Accelerators
从Prefill/Decode阶段差异出发，为新兴AI加速器量身定制LLM推理性能评估方法，助力硬件选型与优化。
arXiv:2606.17104v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, i…