这篇论文戳中了推理模型部署的核心痛点——从计算瓶颈转向容量瓶颈，做 LLM 推理优化的工程师和架构师值得细读，能帮你避开常见的并行策略陷阱。
本文系统研究了从标准生成式 AI 向推理密集型架构（如长链思维模型）转变时，LLM 推理面临的新瓶颈。研究发现，推理工作负载产生大量推理 token，使推理进入“容量受限”阶段，而非传统的计算受限阶段。通过评估 8B 到 671B 参数模型，论文揭示了数据并行在小模型上高效但受 KV 缓存碎片影响，张量并行在 32B 参数附近有次线性增益，而大规模稠密模型受互联和内存带宽限制，稀疏 MoE 模型则受路由和同步延迟限制。这些发现为构建下一代推理基础设施提供了决策框架。
Understanding Inference Scaling for LLMs: Bottlenecks, Trade-offs, and Performance Principles
The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike traditional workloads dominated by compute-bound prefill, reasoning workloads generate long chains of reasoning tokens that shift inference into a \emph{Capacity-Bound regime}. This paper presents a comprehensive system characterization, evaluating models ranging from 8B to 671B parameters on GPUs clusters. By systematically exploring the interplay between Data, Tensor, and Pipeline parallelism, we identify critical bottlenecks that defy standard scaling heuristics. Our analysis reveals that data parallelism is throughput efficient for small models but hits a capacity trap on reasoning workloads as KV-cache fragmentation forces early throttling resulting in sub-optimal compute utilization. Tensor parallelism unlocks stranded memory and delivers sublinear gains near the 32B crossover. At frontier scale, dense models (e.g., Llama-405B) are interconnect and memory-bandwidth bound and favor high-degree TP, while sparse Mixture-of-Experts (MoE) models (e.g., DeepSeek-R1) are limited by routing and synchronization latency and benefit from hybrid strategies. These insights provide a rigorous decision framework for navigating the reasoning cliff, establishing new architectural imperatives for the next generation of inference infrastructure.