45c5bcd962
### What this PR does / why we need it?
Add cudagraph_capture_sizes for E2E CI test.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
Signed-off-by: menogrey <1299267905@qq.com>
71 lines
2.6 KiB
Python
71 lines
2.6 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
# Adapted from vllm/tests/entrypoints/llm/test_guided_generate.py
|
|
# Copyright 2023 The vLLM team.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
from vllm import SamplingParams
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
|
|
|
|
def test_qwen3_topk() -> None:
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
sampling_params = SamplingParams(max_tokens=5,
|
|
temperature=0.0,
|
|
top_k=50,
|
|
top_p=0.9)
|
|
|
|
with VllmRunner("Qwen/Qwen3-0.6B",
|
|
max_model_len=8192,
|
|
cudagraph_capture_sizes=[1, 2, 4, 8],
|
|
gpu_memory_utilization=0.7) as runner:
|
|
runner.generate(example_prompts, sampling_params)
|
|
|
|
|
|
def test_qwen3_prompt_logprobs() -> None:
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
|
|
with VllmRunner("Qwen/Qwen3-0.6B",
|
|
max_model_len=8192,
|
|
cudagraph_capture_sizes=[1, 2, 4, 8],
|
|
gpu_memory_utilization=0.7) as runner:
|
|
runner.generate_greedy_logprobs(example_prompts,
|
|
max_tokens=5,
|
|
num_logprobs=1)
|
|
|
|
|
|
def test_qwen3_exponential_overlap() -> None:
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
sampling_params = SamplingParams(max_tokens=5,
|
|
temperature=1.0,
|
|
top_k=50,
|
|
top_p=0.9)
|
|
|
|
with VllmRunner("Qwen/Qwen3-0.6B",
|
|
max_model_len=8192,
|
|
cudagraph_capture_sizes=[1, 2, 4, 8],
|
|
gpu_memory_utilization=0.7,
|
|
additional_config={
|
|
"enable_async_exponential": True,
|
|
}) as runner:
|
|
runner.generate(example_prompts, sampling_params)
|