You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Measurement study of LLM inference trade-offs across edge-continuum hardware, including accuracy, latency, model footprint, energy, and streaming-delay sensitivity analysis.
About
Measurement study of LLM inference trade-offs across edge-continuum hardware, including accuracy, latency, model footprint, energy, and streaming-delay sensitivity analysis.