57c554a23f
### What this PR does / why we need it?
This PR fixes a bug in the `_merge_multimodal_embeddings` function where
the parameter order was incorrect. The `multimodal_embeddings` and
`is_multimodal` parameters were swapped, which would lead to runtime
errors when the function is called with positional arguments.
This change corrects the function signature to align with its expected
usage, ensuring that multimodal embeddings are correctly merged.
### Does this PR introduce _any_ user-facing change?
No. This is a bug fix for an internal utility function and has no
user-facing impact.
### How was this patch tested?
The correctness of this fix is validated by existing tests for
multimodal functionality. With the incorrect function signature, these
tests would fail due to argument type mismatches. CI passing confirms
the fix is effective.
- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
Signed-off-by: tanhaoan333 <tanhaoan@huawei.com>
59 lines
2.1 KiB
Python
59 lines
2.1 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.
|
|
|
|
import torch
|
|
import vllm
|
|
from vllm.model_executor.models.utils import _embedding_count_expression, _flatten_embeddings
|
|
from vllm.multimodal import NestedTensors
|
|
|
|
|
|
def _merge_multimodal_embeddings(
|
|
inputs_embeds: torch.Tensor,
|
|
multimodal_embeddings: NestedTensors,
|
|
is_multimodal: torch.Tensor,
|
|
) -> torch.Tensor:
|
|
"""
|
|
Merge ``multimodal_embeddings`` into ``inputs_embeds`` by overwriting the
|
|
positions in ``inputs_embeds`` corresponding to placeholder tokens in
|
|
``input_ids``.
|
|
|
|
Note:
|
|
This updates ``inputs_embeds`` in place.
|
|
"""
|
|
flattened = _flatten_embeddings(multimodal_embeddings)
|
|
input_dtype = inputs_embeds.dtype
|
|
try:
|
|
inputs_embeds[is_multimodal] = flattened.to(dtype=input_dtype)
|
|
except RuntimeError as e:
|
|
num_expected_tokens = is_multimodal.sum().item()
|
|
assert isinstance(num_expected_tokens, int)
|
|
|
|
if flattened.shape[0] != num_expected_tokens:
|
|
expr = _embedding_count_expression(multimodal_embeddings)
|
|
raise ValueError(
|
|
f"Attempted to assign {expr} = {flattened.shape[0]} "
|
|
f"multimodal tokens to {num_expected_tokens} placeholders"
|
|
) from e
|
|
else:
|
|
raise ValueError("Error during masked scatter operation") from e
|
|
|
|
return inputs_embeds
|
|
|
|
|
|
vllm.model_executor.models.utils._merge_multimodal_embeddings = _merge_multimodal_embeddings
|