firehose> #llmops

To optimize inference you first have to know what's slowing it down, and AI workloads face two distinct bottlenecks. Compute-bound workloads are limited by available computational power — intensive-calculation tasks like image generation are typically compute-bound. Memory-bandwidth-bound workloads are limited by how fast data moves between memory and processors — and autoregressive language-model inference is typically memory-bandwidth-bound, because generating each token re-reads large weight and KV tensors. The distinction is load-bearing because different optimizations fix different bottlenecks: a compute-bound workload benefits from more powerful chips or distributing work across chips, while a memory-bandwidth-bound workload benefits from chips with higher memory bandwidth (and from techniques like quantization that move less data). Profiling tools (e.g. NVIDIA Nsight) identify which bottleneck applies via a roofline chart.

Claims


Linked from