AI/ llm-serving · gpu-scaling · ai-infrastructure

New Math Pins Down GPU Ratios for Split LLM Serving

A new arXiv paper offers a closed-form rule for balancing Attention and FFN GPUs in disaggregated LLM serving, cutting guesswork and idle time.

A paper posted to arXiv, arXiv:2601.21351, gives LLM infrastructure teams a formula for one of inference serving's most expensive guessing games: how many GPUs to spend on memory versus compute.

The paper studies attention-FFN disaggregation, an architecture that splits LLM decoding into two separate jobs. Attention workers hold the growing KV cache and handle state-heavy lookups; FFN workers do the stateless, compute-heavy math; the two communicate every step. That split lets operators scale memory and compute independently, but performance hinges on getting the ratio of attention to FFN workers right, since a bad ratio leaves workers idle waiting on the slowest step. The authors model the randomness in prompt lengths, decode lengths, and cross-worker synchronization, then derive a closed-form rule for the optimal ratio.

Companies running inference at scale usually tune these ratios by trial and error, burning GPU-hours on test runs or over-provisioning as insurance. A formula that predicts the right split from a single measurable workload statistic could turn that guesswork into a calculation, which matters when idle GPU time is a direct cost.

Worth noting: the validation here comes from a trace-calibrated simulator that matched the true optimum within 10 percent, not a live production fleet, so the real test is whether the math holds up against the messiness of an actual serving cluster.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →