Keep the Agent Warm: How ATOM Serves AgentX Workloads on AMD Instinct MI355X GPUs
AI-generated summary ROCm Blogs describes how ATOM serves Kimi-K3 using AMD Instinct MI355X GPUs on the SemiAnalysis InferenceX AgentX benchmark. ROCm Blogs reports that ATOM uses memory, scheduling, and compute optimizations to handle agentic workloads with long shared histories.