[Misc] format and refactor some examples (#16252)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
This commit is contained in:
@@ -16,14 +16,22 @@ N = 1
|
||||
# Currently, top-p sampling is disabled. `top_p` should be 1.0.
|
||||
sampling_params = SamplingParams(temperature=0, top_p=1.0, n=N, max_tokens=16)
|
||||
|
||||
# Set `enforce_eager=True` to avoid ahead-of-time compilation.
|
||||
# In real workloads, `enforace_eager` should be `False`.
|
||||
llm = LLM(model="Qwen/Qwen2-1.5B-Instruct",
|
||||
max_num_batched_tokens=64,
|
||||
max_num_seqs=4)
|
||||
outputs = llm.generate(prompts, sampling_params)
|
||||
for output, answer in zip(outputs, answers):
|
||||
prompt = output.prompt
|
||||
generated_text = output.outputs[0].text
|
||||
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|
||||
assert generated_text.startswith(answer)
|
||||
|
||||
def main():
|
||||
# Set `enforce_eager=True` to avoid ahead-of-time compilation.
|
||||
# In real workloads, `enforace_eager` should be `False`.
|
||||
llm = LLM(model="Qwen/Qwen2-1.5B-Instruct",
|
||||
max_num_batched_tokens=64,
|
||||
max_num_seqs=4)
|
||||
outputs = llm.generate(prompts, sampling_params)
|
||||
print("-" * 50)
|
||||
for output, answer in zip(outputs, answers):
|
||||
prompt = output.prompt
|
||||
generated_text = output.outputs[0].text
|
||||
print(f"Prompt: {prompt!r}\nGenerated text: {generated_text!r}")
|
||||
assert generated_text.startswith(answer)
|
||||
print("-" * 50)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
Reference in New Issue
Block a user