Files

43 lines
1.8 KiB
Python
Raw Permalink Normal View History

#
# 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
[Main2Main] Upgrade vLLM to 0303 (#6944) ### What this PR does / why we need it? break: - https://github.com/vllm-project/vllm/pull/34102 Disable_full param replaced with valid_modes/invalid_modes API - https://github.com/vllm-project/vllm/pull/35503 Now must return float compilation_time - https://github.com/vllm-project/vllm/pull/35564 New sequence_lengths param added - https://github.com/vllm-project/vllm/pull/33807 A check was performed (if runner_backend != "auto") - https://github.com/vllm-project/vllm/pull/34861 `BaseDeviceCommunicator` now accesses PyTorch's internal `pg_map` to check process group state - https://github.com/vllm-project/vllm/pull/35274 **Important change:** - https://github.com/vllm-project/vllm/pull/28672 `matcher_utils` directly accesses `torch.ops._C.*` during the import phase. In the Ascend environment, some unregistered ops trigger `AttributeError`, causing e2e initialization failure. https://github.com/vllm-project/vllm-ascend/actions/runs/22607260487/job/65502047131#step:10:2323 https://github.com/vllm-project/vllm/blob/main/vllm/compilation/passes/fusion/matcher_utils.py#L29 This PR adds temporary compatibility placeholders (rms_norm, fused_add_rms_norm, rotate_embedding, static/dynamic fp8 quant, silu_and_mul) to `vllm_ascend/patch/platform/patch_fusion_matcher_compat_ops.py` to ensure no crashes during the import phase. Upstream repairs will be considered later. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.16.0 - vLLM main: https://github.com/vllm-project/vllm/commit/15d76f74e2fdb12a95ea00f0ca283acf6219a2b7 --------- Signed-off-by: MrZ20 <2609716663@qq.com> Signed-off-by: gcanlin <canlinguosdu@gmail.com> Co-authored-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: Claude Code <noreply@anthropic.com> Co-authored-by: gcanlin <canlinguosdu@gmail.com>
2026-03-06 09:08:52 +08:00
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
[Lint]Style: Convert `vllm-ascend/` to ruff format(Batch #6) (#6001) ### What this PR does / why we need it? | File Path | | :--- | | ` vllm_ascend/eplb/adaptor/abstract_adaptor.py` | | ` vllm_ascend/eplb/adaptor/vllm_adaptor.py` | | ` vllm_ascend/eplb/core/eplb_device_transfer_loader.py` | | ` vllm_ascend/eplb/core/eplb_utils.py` | | ` vllm_ascend/eplb/core/eplb_worker.py` | | ` vllm_ascend/eplb/core/policy/policy_abstract.py` | | ` vllm_ascend/eplb/core/policy/policy_default_eplb.py` | | ` vllm_ascend/eplb/core/policy/policy_factory.py` | | ` vllm_ascend/eplb/core/policy/policy_flashlb.py` | | ` vllm_ascend/eplb/core/policy/policy_random.py` | | ` vllm_ascend/eplb/core/policy/policy_swift_balancer.py` | | ` vllm_ascend/eplb/eplb_updator.py` | | ` vllm_ascend/eplb/utils.py` | | ` vllm_ascend/model_loader/netloader/executor/elastic_load.py` | | ` vllm_ascend/model_loader/netloader/executor/netloader_pg.py` | | ` vllm_ascend/model_loader/netloader/interaction/elastic.py` | | ` vllm_ascend/model_loader/netloader/load.py` | | ` vllm_ascend/model_loader/netloader/netloader.py` | | ` vllm_ascend/model_loader/netloader/utils.py` | | ` vllm_ascend/patch/platform/__init__.py` | | ` vllm_ascend/patch/platform/patch_balance_schedule.py` | | ` vllm_ascend/patch/platform/patch_ec_connector.py` | | ` vllm_ascend/patch/platform/patch_mamba_config.py` | | ` vllm_ascend/patch/platform/patch_multiproc_executor.py` | | ` vllm_ascend/patch/platform/patch_sched_yield.py` | - vLLM version: v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/2c24bc6996cb165fce92f780b388a5e39b3f4060 --------- Signed-off-by: MrZ20 <2609716663@qq.com>
2026-01-24 22:08:33 +08:00
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
2026-04-21 03:05:32 +00:00
import vllm_ascend.patch.platform.patch_executor # noqa
import vllm_ascend.patch.platform.patch_core # noqa