Update README.md

README.md

@@ -42,7 +42,7 @@ sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
 
 if __name__ == '__main__':
     # Create an LLM.
-    llm = LLM(model="pytorch/Phi-4-mini-instruct-int4wo-hqq")
+    llm = LLM(model="pytorch/Qwen3-8B-int4wo-hqq")
     # Generate texts from the prompts.
     # The output is a list of RequestOutput objects
     # that contain the prompt, generated text, and other information.
@@ -63,7 +63,8 @@ this is expected be resolved in pytorch 2.8.
 ## Serving
 Then we can serve with the following command:
 ```Shell
-vllm serve pytorch/Phi-4-mini-instruct-int4wo-hqq --tokenizer microsoft/Phi-4-mini-instruct -O3
+export MODEL=pytorch/Qwen3-8B-int4wo-hqq
+vllm serve $MODEL --tokenizer $MODEL -O3
 ```
 
 
@@ -84,7 +85,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
  
 torch.random.manual_seed(0)
 
-model_path = "pytorch/Phi-4-mini-instruct-int4wo-hqq"
+model_path = "pytorch/Qwen3-8B-int4wo-hqq"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_path,
@@ -282,9 +283,9 @@ Our int4wo is only optimized for batch size 1, so expect some slowdown with larg
 ## Results (A100 machine)
 | Benchmark (Latency)              |                |                          |
 |----------------------------------|----------------|--------------------------|
-|                                  | Phi-4 mini-Ins | phi4-mini-int4wo-hqq     | 
-| latency (batch_size=1)           | 2.46s          | 2.2s (12% speedup)       |
-| serving (num_prompts=1)          | 0.87 req/s     | 1.05 req/s (20% speedup) |
+|                                  | Qwen3-8B       | Qwen3-8B-int4wo-hqq      | 
+| latency (batch_size=1)           | TODOs          | TODOs (TODO% speedup)       |
+| serving (num_prompts=1)          | TODO req/s     | TODO req/s (20% speedup) |
 
 Note the result of latency (benchmark_latency) is in seconds, and serving (benchmark_serving) is in number of requests per second.
 Int4 weight only is optimized for batch size 1 and short input and output token length, please stay tuned for models optimized for larger batch sizes or longer token length.