53cc225cac
### What this PR does / why we need it? This backports the MiniMax M2 reasoning-token usage accounting fix onto `releases/v0.18.0` for vllm-ascend. The release branch does not include the other local GLM patch commit, so this PR keeps the MiniMax change self-contained by: - registering `patch_minimax_usage_accounting` on the release branch - backporting `completion_tokens_details.reasoning_tokens` into chat usage generation - fixing MiniMax reasoning token counting for `</think>`-delimited outputs without depending on the GLM suffix patch ### Does this PR introduce _any_ user-facing change? Yes. OpenAI-compatible chat usage accounting for MiniMax M2 responses now reports corrected reasoning token counts on the release branch. ### How was this patch tested? - `python -m compileall vllm_ascend/patch/platform/patch_minimax_usage_accounting.py` - `python - <<'PY'` import check for `vllm_ascend.patch.platform.patch_minimax_usage_accounting` on top of `releases/v0.18.0` No targeted automated regression test exists for this release-branch backport yet, so I validated syntax and module import compatibility on the release branch. --------- Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com> Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
39 lines
1.6 KiB
Python
39 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 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
|
|
|
|
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
|