Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
53 lines
1.3 KiB
Python
53 lines
1.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
import time
|
|
|
|
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",
|
|
tensor_parallel_size=1,
|
|
profiler_config={
|
|
"profiler": "torch",
|
|
"torch_profiler_dir": "./vllm_profile",
|
|
},
|
|
)
|
|
|
|
llm.start_profile()
|
|
|
|
# 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)
|
|
|
|
llm.stop_profile()
|
|
|
|
# Print the outputs.
|
|
print("-" * 50)
|
|
for output in outputs:
|
|
prompt = output.prompt
|
|
generated_text = output.outputs[0].text
|
|
print(f"Prompt: {prompt!r}\nGenerated text: {generated_text!r}")
|
|
print("-" * 50)
|
|
|
|
# Add a buffer to wait for profiler in the background process
|
|
# (in case MP is on) to finish writing profiling output.
|
|
time.sleep(10)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|