4970de4242
### What this PR does / why we need it?
Enable the tests that were skipped due to an outdated driver version:
- tests/e2e/multicard/4-cards/long_sequence/test_accuracy.py
- tests/e2e/multicard/4-cards/long_sequence/test_basic.py
- tests/e2e/multicard/4-cards/long_sequence/test_chunked_prefill.py
and some cases in
- tests/e2e/multicard/2-cards/spec_decode/test_spec_decode.py
- tests/e2e/multicard/2-cards/test_external_launcher.py
- tests/e2e/multicard/2-cards/test_offline_weight_load.py
- tests/e2e/multicard/2-cards/test_quantization.py
- tests/e2e/multicard/4-cards/test_data_parallel_tp2.py
TODO:
- tests/e2e/multicard/4-cards/spec_decode/test_mtp_qwen3_next.py
- tests/e2e/multicard/4-cards/long_sequence/test_mtp.py
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.0
- vLLM main:
d68209402d
Signed-off-by: wjunLu <wjunlu217@gmail.com>
67 lines
2.2 KiB
Python
67 lines
2.2 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
|
|
#
|
|
import pytest
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
|
|
|
|
def test_qwen2_5_w8a8_external_quantized_tp2():
|
|
example_prompts = [
|
|
"The president of the United States is",
|
|
]
|
|
max_tokens = 5
|
|
with VllmRunner(
|
|
"neuralmagic/Qwen2.5-3B-quantized.w8a8",
|
|
tensor_parallel_size=2,
|
|
cudagraph_capture_sizes=[1, 2, 4, 8],
|
|
max_model_len=4096,
|
|
gpu_memory_utilization=0.8,
|
|
) as vllm_model:
|
|
vllm_output = vllm_model.generate_greedy(example_prompts, max_tokens)
|
|
|
|
golden_results = [
|
|
'The president of the United States is the head of state and',
|
|
]
|
|
|
|
for i in range(len(vllm_output)):
|
|
assert golden_results[i] == vllm_output[i][1]
|
|
print(f"Generated text: {vllm_output[i][1]!r}")
|
|
|
|
|
|
def test_qwen3_moe_w8a8_dynamic_llm_compressor():
|
|
example_prompts = [
|
|
"The president of the United States is",
|
|
]
|
|
max_tokens = 5
|
|
with VllmRunner(
|
|
"vllm-ascend/Qwen3-30B-A3B-Instruct-2507-quantized.w8a8",
|
|
tensor_parallel_size=2,
|
|
max_model_len=4096,
|
|
gpu_memory_utilization=0.8,
|
|
) as vllm_model:
|
|
vllm_output = vllm_model.generate_greedy(example_prompts, max_tokens)
|
|
|
|
golden_results = [
|
|
'The president of the United States is the head of state and',
|
|
]
|
|
|
|
for i in range(len(vllm_output)):
|
|
assert golden_results[i] == vllm_output[i][1]
|
|
print(f"Generated text: {vllm_output[i][1]!r}")
|