FDEBench Join us live

Q
134 / 159

Training & fine-tuning

Why can LLM training be parallelized, and where does that break down?

youtube Keerti Purswani - 20 Agentic AI System Design Questions Source

01
Open

No reference answer yet

This question is in the bank but has no rubric written for it. It can be read and practised, but not scored.

—

PreviousHow would you design a scalable system for training an LLM under both compute and data con… NextA sharded database routes by user_id modulo shard count. The team wants to add a shard. Ex…