fef18b60bc
Refactor E2E CI to make it clear and faster
1. remove some uesless e2e test
2. remove some uesless function
3. Make sure all test runs with VLLMRunner to avoid oom error
4. Make sure all ops test end with torch.empty_cache to avoid oom error
5. run the test one by one to avoid resource limit error
- vLLM version: v0.10.1.1
- vLLM main:
a344a5aa0a
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
75 lines
2.6 KiB
Python
75 lines
2.6 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-project/vllm/blob/main/tests/models/utils.py
|
|
#
|
|
|
|
from typing import Dict, List, Optional, Sequence, Tuple, Union
|
|
|
|
from vllm.sequence import PromptLogprobs, SampleLogprobs
|
|
|
|
TokensText = Tuple[List[int], str]
|
|
|
|
|
|
def check_outputs_equal(
|
|
*,
|
|
outputs_0_lst: Sequence[TokensText],
|
|
outputs_1_lst: Sequence[TokensText],
|
|
name_0: str,
|
|
name_1: str,
|
|
):
|
|
"""
|
|
Compare the two sequences generated by different models,
|
|
which should be equal.
|
|
"""
|
|
assert len(outputs_0_lst) == len(outputs_1_lst)
|
|
|
|
for prompt_idx, (outputs_0,
|
|
outputs_1) in enumerate(zip(outputs_0_lst,
|
|
outputs_1_lst)):
|
|
output_ids_0, output_str_0 = outputs_0
|
|
output_ids_1, output_str_1 = outputs_1
|
|
|
|
# The text and token outputs should exactly match
|
|
fail_msg = (f"Test{prompt_idx}:"
|
|
f"\n{name_0}:\t{output_str_0!r}"
|
|
f"\n{name_1}:\t{output_str_1!r}")
|
|
|
|
assert output_str_0 == output_str_1, fail_msg
|
|
assert output_ids_0 == output_ids_1, fail_msg
|
|
|
|
|
|
# Representation of generated sequence as a tuple of
|
|
# * Token ID list
|
|
# * String
|
|
# * List of top sample logprobs for each sampled token
|
|
#
|
|
# Assumes prompt logprobs were not requested.
|
|
TokensTextLogprobs = Tuple[List[int], str, Optional[Union[List[Dict[int,
|
|
float]],
|
|
SampleLogprobs]]]
|
|
|
|
# Representation of generated sequence as a tuple of
|
|
# * Token ID list
|
|
# * String
|
|
# * Optional list of top sample logprobs for each sampled token
|
|
# * Optional list of top prompt logprobs for each prompt token
|
|
#
|
|
# Allows prompt logprobs to be requested.
|
|
TokensTextLogprobsPromptLogprobs = Tuple[
|
|
List[int], str, Optional[Union[List[Dict[int, float]], SampleLogprobs]],
|
|
Optional[Union[List[Optional[Dict[int, float]]], PromptLogprobs]]]
|