Is Clearml-Serving Using Either System Or Cuca Shared Memory? Or Planning To? In Our Experiments Using Perf_Analyzer The Shared Memory Experiments Showed A Huge Improvement And If We Wanted To Look Into This, Do You Have Any Pointers Of Where We Can Do T

Unanswered

Hi @<1547028116780617728:profile|TimelyRabbit96>
Notice that if running with docker compose you can pass an argument to the clearml triton container an use shared mem. You can do the same with the helm chart

  				
Posted 
	8 months ago

					More
				  		
  Report
		
					AgitatedDove14
				
					0
					 × 1

103 Views

0 Answers

8 months ago