Update README.md

README.md

@@ -75,7 +75,7 @@ However, it is still fundamentally limited by its size for certain tasks. The mo
  
 ### Model Efficiency
 
-The two figures below compare the latency and throughput performance of the Phi-4-mini-reasoning and Phi-4-mini-flash-reasoning models under the vLLM inference framework. All evaluations were performed on a single NVIDIA A100-80GB GPU with tensor parallelism disabled (TP = 1). The Phi-4-mini-flash-reasoning model, which incorporates a decoder-hybrid-decoder architecture with attention and state space model (SSM), exhibits significantly greater computational efficiency—achieving a 2–3× reduction in average latency and up-to a 10× improvement in throughput when processing user requests with 2K prompt length and 32K generation length. Furthermore, Phi-4-mini-flash-reasoning demonstrates near-linear growth in latency with respect to the number of tokens generated (up to 32k), in contrast to the quadratic growth observed in Phi-4-mini-reasoning. These findings indicate that Phi-4-mini-flash-reasoning is more scalable and better suited for long-sequence generation tasks.
+The two figures below compare the latency and throughput performance of the Phi-4-mini-reasoning and Phi-4-mini-flash-reasoning models under the vLLM inference framework. All evaluations were performed on a single NVIDIA A100-80GB GPU with tensor parallelism disabled (TP = 1). The Phi-4-mini-flash-reasoning model, which incorporates a decoder-hybrid-decoder architecture with attention and state space model (SSM), exhibits significantly greater computational efficiency—achieving up-to a 10× improvement in throughput when processing user requests with 2K prompt length and 32K generation length. Furthermore, Phi-4-mini-flash-reasoning demonstrates near-linear growth in latency with respect to the number of tokens generated (up to 32k), in contrast to the quadratic growth observed in Phi-4-mini-reasoning. These findings indicate that Phi-4-mini-flash-reasoning is more scalable and better suited for long-sequence generation tasks.
 
 <div align="left">
   <img src="lat.png" width="300"/>