f83cb0e6dc
### What this PR does / why we need it? This rebases the GLM47 tool-call parser fix onto `releases/v0.18.0` after the MiniMax usage-accounting patch merged upstream on March 27, 2026. It fixes OpenAI chat tool-call streaming for GLM47 by: - draining terminal parser chunks that contain both the final argument text and the closing `</tool_call>` suffix - computing finish backfill from the tool argument bytes actually emitted to the client, instead of trusting parser-internal buffered state - adding focused regression tests for finish backfill and terminal chunk handling ### Does this PR introduce _any_ user-facing change? Yes. GLM47 OpenAI-compatible streaming tool-call responses now emit correct final chunks and argument payloads on `releases/v0.18.0`. ### How was this patch tested? - `pytest -q tests/ut/patch/platform/test_patch_glm_tool_call_parser.py tests/ut/patch/platform/test_patch_minimax_usage_accounting.py` - `python -m pre_commit run --files vllm_ascend/patch/platform/patch_glm_tool_call_parser.py tests/ut/patch/platform/test_patch_glm_tool_call_parser.py vllm_ascend/patch/platform/__init__.py vllm_ascend/patch/__init__.py` --------- Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com> Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
40 lines
1.7 KiB
Python
40 lines
1.7 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 os
|
|
|
|
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_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
|
|
|
|
if os.getenv("DYNAMIC_EPLB", "false").lower() in ("true", "1") or os.getenv("EXPERT_MAP_RECORD", "false") == "true":
|
|
import vllm_ascend.patch.platform.patch_multiproc_executor # noqa
|
|
|
|
if envs.VLLM_ASCEND_BALANCE_SCHEDULING:
|
|
import vllm_ascend.patch.platform.patch_balance_schedule # noqa
|