8f6f967028
### What this PR does / why we need it? Add e2e test and accuracy test for Qwen3-Next-80B-A3B-Instruct ### How was this patch tested? accuracy test: https://github.com/vllm-project/vllm-ascend/actions/runs/18771221544/job/53556027634?pr=3450 ci test: https://github.com/vllm-project/vllm-ascend/actions/runs/18771221530/job/53556027614?pr=3450 <img width="1703" height="562" alt="image" src="https://github.com/user-attachments/assets/973b6cfa-8240-41e3-893a-5024ff8d0693" /> - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 Signed-off-by: hfadzxy <starmoon_zhang@163.com>
39 lines
1.4 KiB
Python
39 lines
1.4 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# 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.
|
|
# This file is a part of the vllm-ascend project.
|
|
# Adapted from vllm/tests/basic_correctness/test_basic_correctness.py
|
|
#
|
|
"""Compare the short outputs of HF and vLLM when using greedy sampling.
|
|
|
|
Run `pytest tests/e2e/multicard/test_qwen3_next.py`.
|
|
"""
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
|
|
|
|
def test_models_distributed_Qwen3_NEXT_TP4():
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
max_tokens = 5
|
|
with VllmRunner("Qwen/Qwen3-Next-80B-A3B-Instruct",
|
|
tensor_parallel_size=4,
|
|
max_model_len=4096,
|
|
gpu_memory_utilization=0.7,
|
|
distributed_executor_backend="mp",
|
|
enforce_eager=True) as vllm_model:
|
|
vllm_model.generate_greedy(example_prompts, max_tokens)
|