Update README.md

README.md

@@ -98,6 +98,15 @@ lm_eval --model hf --model_args pretrained=jerryzh168/phi4-mini-float8dq --tasks
  
 # Model Performance
 
+## Results (H100 machine)
+| Benchmark                        |                |                          |
+|----------------------------------|----------------|--------------------------|
+|                                  | Phi-4 mini-Ins | phi4-mini-float8dq       | 
+| latency (batch_size=1)           | 1.64 s         | 1.41s (16% speedup)      |
+| latency (batch_size=128)         | 3.1 s          | 2.72s (14% speedup)      |
+| serving (num_prompts=1)          | 1.35 req/s     | 1.57 req/s (16% speedup) |
+| serving (num_prompts=1000)       | 66.68 req/s    | 80.53 req/s (21% speedup)|
+
 ## Download vllm source code and install vllm
 ```
 git clone [email protected]:vllm-project/vllm.git