02f89d166f
### What this PR does / why we need it? This pr bump vllm commit hash to5aeb925452fix issues: 1. https://github.com/vllm-project/vllm/pull/25345 has remove v0 metadata 2. https://github.com/vllm-project/vllm/pull/25332 3. https://github.com/vllm-project/vllm/pull/25334 4. https://github.com/vllm-project/vllm/pull/23558, note that this vllm commit update the model register logic, which will check all the model registered have the `vllm.model_executor.models` path , which breaks our custom registration of the deepseek_v3 model (it doesn't exist in the vllm model path). so I move deepseek_v3 model registy to deepseek_v2 to solve temporary ### How was this patch tested? - vLLM version: v0.10.2 - vLLM main:9607d5eb44--------- Signed-off-by: wangli <wangli858794774@gmail.com>
80 lines
2.7 KiB
Python
80 lines
2.7 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_ascend.utils import vllm_version_is
|
|
|
|
if vllm_version_is("0.10.2"):
|
|
from vllm.sequence import PromptLogprobs, SampleLogprobs
|
|
else:
|
|
from vllm.logprobs 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]]]
|