← Knowledge Base

Concept

Pipelining

Splitting a model across racks layer-wise so each rack handles a slice of the forward pass, used heavily in training and selectively in inference.

Tensions

Pipelining solves weight-capacity problems cleanly but does nothing for KV cache (per-GPU activation footprint is invariant) and adds milliseconds of latency per hop. In inference it is often skipped — modern racks already hold a trillion-parameter model — but it lets hardware designers cut HBM-per-GPU if they assume the model spans multiple racks.

Related Concepts

parallelism | scale-up domain | KV cache | memory bandwidth | latency

Last updated: May 17, 2026