Update README.md

README.md

@@ -95,37 +95,37 @@ lm_eval --model hf --model_args pretrained=jerryzh168/phi4-mini-float8dq --tasks
  
 # Model Performance
 
-# Download vllm source code and install vllm
+## Download vllm source code and install vllm
 ```
 git clone [email protected]:vllm-project/vllm.git
 VLLM_USE_PRECOMPILED=1 pip install .
 ```
 
-# Download dataset
+## Download dataset
 Download sharegpt dataset: `wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json`
 
 Other datasets can be found in: https://github.com/vllm-project/vllm/tree/main/benchmarks
-# benchmark_latency
+## benchmark_latency
 
 Run the following under `vllm` source code root folder:
 
-## baseline
+### baseline
 ```
 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model microsoft/Phi-4-mini-instruct --batch-size 1
 ```
 
-## float8dq
+### float8dq
 ```
 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model jerryzh168/phi4-mini-float8dq --batch-size 1
 ```
 
-# benchmark_serving
+## benchmark_serving
 
 We also benchmarked the throughput in a serving environment.
 
 Run the following under `vllm` source code root folder:
 
-## baseline
+### baseline
 Server:
 ```
 vllm serve microsoft/Phi-4-mini-instruct --tokenizer microsoft/Phi-4-mini-instruct -O3
@@ -136,7 +136,7 @@ Client:
 python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --tokenizer microsoft/Phi-4-mini-instruct --dataset-path ./ShareGPT_V3_unfiltered_cleaned_split.json --model microsoft/Phi-4-mini-instruct --num-prompts 1
 ```
 
-## float8dq
+### float8dq
 Server:
 ```
 vllm serve jerryzh168/phi4-mini-float8dq --tokenizer microsoft/Phi-4-mini-instruct -O3