🔧 99.8% of LLM Inference Power Isn't Spent on Computation

99.8% of LLM Inference Power Isn't Spent on Computation


When people debate LLM inference bottlenecks, bandwidth and VRAM dominate the conversation. But of the five walls identified by LIMINAL (Davies et al., arXiv:2507.14397), the hardest one to break through is power.

Bandwidth scales by widening the bus (HBM4 did exactly that). Capacity...