Update README.md

README.md

@@ -15,10 +15,18 @@ For more details about SwiftKV and how to use it:
 
 ## Performance Metrics
 
-Combined input and output throughput for Llama 3.1 405B across a range of input lengths.
+To evaluate SwiftKV’s performance, we focus on the following key metrics:
+* Combined throughput: The total number of input and output tokens processed per second. This determines:
+For batch processing, the time required to complete jobs.
+For interactive use, the volume of concurrent requests a system can handle.
+* TTFT: The latency between a user request and receiving the first token in the response.
+* TPOT: The latency between subsequent tokens after the first token.
+
+Combined input and output throughput for Llama 3.1 405B across a range of input lengths. Blue is baseline FP8 and Ping is SwiftKV FP8.
 <img src="figure-4.png" alt="performance plot of llama-405B w. swiftkv" width="400">
-Legend: blue - baseline FP8, pink - SwiftKV FP8<br>
 
+TTFT (top) and TPOT (bottom) for input lengths 2000 (left), 8000 (middle), and 32000 (right) for Llama 3.1 405B fp8 model. For each experiment, a range of different request arrival rates is simulated. Each request generates 256 output tokens. 
+<img src="figure-6.png" alt="performance plot of llama-405B w. swiftkv" width="700">
 
 
 ## Eval Metrics