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>
28 lines
909 B
Python
28 lines
909 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from vllm import LLM, SamplingParams
|
|
|
|
|
|
def test_gpu_memory_utilization():
|
|
prompts = [
|
|
"Hello, my name is",
|
|
"The president of the United States is",
|
|
"The capital of France is",
|
|
"The future of AI is",
|
|
]
|
|
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
|
|
|
|
# makes sure gpu_memory_utilization is per-instance limit,
|
|
# not a global limit
|
|
llms = [
|
|
LLM(model="facebook/opt-125m", gpu_memory_utilization=0.3, enforce_eager=True)
|
|
for i in range(3)
|
|
]
|
|
for llm in llms:
|
|
outputs = llm.generate(prompts, sampling_params)
|
|
for output in outputs:
|
|
prompt = output.prompt
|
|
generated_text = output.outputs[0].text
|
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|