[Examples][1/n] Resettle basic examples. (#35579)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io> Signed-off-by: wang.yuqi <noooop@126.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
35
examples/basic/offline_inference/basic.py
Normal file
35
examples/basic/offline_inference/basic.py
Normal file
@@ -0,0 +1,35 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
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)
|
||||
|
||||
|
||||
def main():
|
||||
# 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.
|
||||
print("\nGenerated Outputs:\n" + "-" * 60)
|
||||
for output in outputs:
|
||||
prompt = output.prompt
|
||||
generated_text = output.outputs[0].text
|
||||
print(f"Prompt: {prompt!r}")
|
||||
print(f"Output: {generated_text!r}")
|
||||
print("-" * 60)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user