Power Capping
Cross-source consensus on Power Capping from 1 sources and 4 claims.
1 sources · 4 claims
Uses
How it works
Comparisons
Evidence quality
Highlighted claims
- Power capping is ineffective for memory-bound LLM decode when actual draw remains below the configured ceiling. — The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
- Decode power draw on the tested H200 stayed far below its 700 W TDP across attention paradigms. — The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
- Changing configured power caps by 2.5x barely changed actual power or clocks in a batch-size-1 decode measurement. — The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
- Facility-level power capping should not be assumed to reduce decode energy in production LLM serving. — The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures