[Dev] Add vllm example

bazel/python/requirements.txt

@@ -3,3 +3,4 @@ Werkzeug==2.2.2
 Flask==2.0.2
 kubernetes==27.2.0
 depyf
+vllm

experimental/vllm_example/BUILD

@@ -0,0 +1,11 @@
+load("@pip//:requirements.bzl", "requirement")
+load("@rules_python//python:defs.bzl", "py_binary", "py_library")
+
+py_binary(
+    name = "simple_inference",
+    srcs = ["simple_inference.py"],
+    main = "simple_inference.py",
+    deps = [
+        requirement("vllm"),
+    ],
+)

experimental/vllm_example/README.md

@@ -0,0 +1,4 @@
+## vllm
+
+### References
+- [vllm](https://github.com/vllm/vllm)

experimental/vllm_example/simple_inference.py

@@ -0,0 +1,22 @@
+from vllm import LLM, SamplingParams
+
+# Sample prompts.
+prompts = [
+    "Hello, my name is",
+    "The president of the United States is",
+    "The capital of France is",
+    "The future of AI is",
+]
+# Create a sampling params object.
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+# Create an LLM.
+llm = LLM(model="facebook/opt-125m")
+# Generate texts from the prompts. The output is a list of RequestOutput objects
+# that contain the prompt, generated text, and other information.
+outputs = llm.generate(prompts, sampling_params)
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")