update docs for Yi-VL

README.md

@@ -357,9 +357,11 @@ python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port
 - Llama
 - Mistral
 - Mixtral
+- Qwen / Qwen 2
 - LLaVA
   - `python3 -m sglang.launch_server --model-path liuhaotian/llava-v1.5-7b --tokenizer-path llava-hf/llava-1.5-7b-hf --chat-template vicuna_v1.1 --port 30000`
-- Qwen / Qwen 2
+- Yi-VL
+  - see [srt_example_yi_vl.py](examples/quick_start/srt_example_yi_vl.py).
 - AWQ quantization
 
 ## Benchmark And Performance

examples/quick_start/srt_example_yi_vl.py

@@ -46,12 +46,9 @@ def batch():
 
 
 if __name__ == "__main__":
-    runtime = sgl.Runtime(model_path="BabyChou/Yi-VL-6B",
-                          tokenizer_path="BabyChou/Yi-VL-6B")
+    runtime = sgl.Runtime(model_path="BabyChou/Yi-VL-6B")
+    # runtime = sgl.Runtime(model_path="BabyChou/Yi-VL-34B")
     sgl.set_default_backend(runtime)
-    # Or you can use API models
-    # sgl.set_default_backend(sgl.OpenAI("gpt-4-vision-preview"))
-    # sgl.set_default_backend(sgl.VertexAI("gemini-pro-vision"))
 
     # Run a single request
     print("\n========== single ==========\n")
@@ -65,4 +62,4 @@ if __name__ == "__main__":
     print("\n========== batch ==========\n")
     batch()
 
-    runtime.shutdown()
\ No newline at end of file
+    runtime.shutdown()