d81101acdd
### What this PR does / why we need it? This backports the forced-tool-choice `content=None` guard to the `releases/v0.18.0` compatibility layer. Upstream vLLM still has forced named tool-choice branches that assert `content is not None` after reasoning extraction. Some reasoning parsers can legally consume the full output and return `(reasoning, None)`, which makes the assert reachable and can surface as a server-side failure. This PR follows the same compatibility-patch pattern used by: - `7314bbe2` fix(platform): reimplement MiniMax usage accounting patch (#7835) - `f83cb0e6` [Bugfix][Platform] Fix GLM47 tool-call finish backfill (#7710) The patch is intentionally narrow: - normalize `content=None` to `""` only for forced named tool choice - patch both chat-completions and responses parser entry points - keep the rest of upstream behavior unchanged Upstream tracking: - issue: vllm-project/vllm#40147 - PR: vllm-project/vllm#40148 ### Does this PR introduce _any_ user-facing change? Yes. Forced named tool choice becomes robust when the reasoning parser returns no post-reasoning content, avoiding an internal assertion failure and emitting an empty-argument function call instead. ### How was this patch tested? Unit tests: ```bash pytest -sv tests/ut/patch/platform/test_patch_tool_choice_none_content.py \ tests/ut/patch/platform/test_patch_glm_tool_call_parser.py \ tests/ut/patch/platform/test_patch_minimax_usage_accounting.py ``` Result: 22 passed. --------- Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com> Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
37 lines
1.6 KiB
Python
37 lines
1.6 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
# 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.
|
|
|
|
import vllm_ascend.patch.platform.patch_distributed # noqa
|
|
import vllm_ascend.patch.platform.patch_fusion_matcher_compat_ops # noqa
|
|
import vllm_ascend.patch.platform.patch_kv_cache_interface # noqa
|
|
from vllm_ascend import envs
|
|
from vllm_ascend.utils import is_310p
|
|
|
|
if not is_310p():
|
|
import vllm_ascend.patch.platform.patch_mamba_config # noqa
|
|
else:
|
|
import vllm_ascend.patch.platform.patch_mamba_config_310 # noqa
|
|
import vllm_ascend.patch.platform.patch_minimax_m2_config # noqa
|
|
import vllm_ascend.patch.platform.patch_multiproc_executor # noqa
|
|
import vllm_ascend.patch.platform.patch_sched_yield # noqa
|
|
import vllm_ascend.patch.platform.patch_torch_accelerator # noqa
|
|
import vllm_ascend.patch.platform.patch_minimax_usage_accounting # noqa
|
|
import vllm_ascend.patch.platform.patch_glm_tool_call_parser # noqa
|
|
import vllm_ascend.patch.platform.patch_tool_choice_none_content # noqa
|
|
|
|
if envs.VLLM_ASCEND_BALANCE_SCHEDULING:
|
|
import vllm_ascend.patch.platform.patch_balance_schedule # noqa
|