Update README.md

README.md

@@ -81,7 +81,7 @@ The two figures below compare the latency and throughput performance of the Phi-
   <img src="lat.png" width="300"/>
   <img src="thr_lat.png" width="298"/>
 </div>
-Figure 1. The first plot shows average inference latency as a function of generation length, while the second plot illustrates how inference latency varies with throughput. Both experiments were conducted using the vLLM inference framework on a single A100-80GB GPU over various number of concurrent requests. 
+Figure 1. The first plot shows average inference latency as a function of generation length, while the second plot illustrates how inference latency varies with throughput. Both experiments were conducted using the vLLM inference framework on a single A100-80GB GPU over varying concurrency levels of user requests. 
 
 ## Usage