1cc225711d
### What this PR does / why we need it? This pull request significantly enhances the test suite by adding new end-to-end test cases for Qwen3 models on the 310P hardware platform. The primary goal is to ensure the stability and correctness of these models under diverse operational conditions, including various parallelism strategies, data types, and quantization methods. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? E2E test - vLLM version: v0.15.0 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0 --------- Signed-off-by: pu-zhe <zpuaa@outlook.com>
47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
#
|
|
# Copyright (c) 2026 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.
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
|
|
|
|
def test_qwen3_dense_tp1_fp16():
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
max_tokens = 5
|
|
with VllmRunner(
|
|
"Qwen/Qwen3-8B",
|
|
tensor_parallel_size=1,
|
|
enforce_eager=True,
|
|
dtype="float16"
|
|
) as vllm_model:
|
|
vllm_model.generate_greedy(example_prompts, max_tokens)
|
|
|
|
def test_qwen3_dense_tp1_w8a8():
|
|
example_prompts = [
|
|
"Hello, my name is",
|
|
]
|
|
max_tokens = 5
|
|
with VllmRunner(
|
|
"vllm-ascend/Qwen3-8B-W8A8",
|
|
tensor_parallel_size=1,
|
|
enforce_eager=True,
|
|
dtype="float16",
|
|
quantization="ascend"
|
|
) as vllm_model:
|
|
vllm_model.generate_greedy(example_prompts, max_tokens)
|