Tag
预告在 PyTorch Conference North America 上，来自 AMD 的 Huanran Wang 将展示海报 FlexBudget：在统一的 FlexAttention 编译内核与固定显存预算下，只替换 KV 重要性规则，从而对长上下文 KV cache 丢弃策略做公平、免训练的对比。
The article discusses how LLMs have grown increasingly complex, moving beyond simple transformer stacks to incorporate diverse attention variants, mixture-of-experts, and multimodal encoders, drawing parallels with recommendation systems and emphasizing the need for composable kernel optimization like FlexAttention.