05bdcbeae4
<!-- Thanks for sending a pull request! BEFORE SUBMITTING, PLEASE READ https://docs.vllm.ai/en/latest/contributing/overview.html --> ### What this PR does / why we need it? <!-- - Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue. If possible, please consider writing useful notes for better and faster reviews in your PR. - Please clarify why the changes are needed. For instance, the use case and bug description. - Fixes # --> This PR supports the access of vllm-acend to the piecewise_graph feature provided by the v1 engine. 1. register unifiled_ascend_attention_with_output for piecewise_graph to split graph. 2. support NPUGraph to accelerate kernel launch. ### Does this PR introduce _any_ user-facing change? <!-- Note that it means *any* user-facing change including all aspects such as API, interface or other behavior changes. Documentation-only updates are not considered user-facing changes. --> support npugraph to default， Users can disenable the npugraph feature by configuring enforce_eager. This has corresponding requirements for the versions of torch_npu and CANN, and they need to support graph capture. ### How was this patch tested? <!-- CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. --> it turn to default --------- Signed-off-by: Bug Hunter Yan <yanpq@zju.edu.cn> Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com>
51 lines
1.9 KiB
Python
51 lines
1.9 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
#
|
|
# 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 torch_npu # noqa: F401
|
|
|
|
import vllm_ascend.ops.activation # noqa
|
|
import vllm_ascend.ops.fused_moe # noqa
|
|
import vllm_ascend.ops.layernorm # noqa
|
|
import vllm_ascend.ops.rotary_embedding # noqa
|
|
import vllm_ascend.ops.vocab_parallel_embedding # noqa
|
|
|
|
|
|
class dummyFusionOp:
|
|
default = None
|
|
|
|
def __init__(self, name=""):
|
|
self.name = name
|
|
|
|
|
|
def register_dummy_fusion_op() -> None:
|
|
torch.cuda.CUDAGraph = torch_npu.npu.NPUGraph
|
|
torch.ops._C.rms_norm = dummyFusionOp(name="rms_norm")
|
|
torch.ops._C.fused_add_rms_norm = dummyFusionOp(name="fused_add_rms_norm")
|
|
torch.ops._C.static_scaled_fp8_quant = dummyFusionOp(
|
|
name="static_scaled_fp8_quant")
|
|
torch.ops._C.dynamic_scaled_fp8_quant = dummyFusionOp(
|
|
name="dynamic_scaled_fp8_quant")
|
|
torch.ops._C.dynamic_per_token_scaled_fp8_quant = dummyFusionOp(
|
|
name="dynamic_per_token_scaled_fp8_quant")
|
|
torch.ops._C.rms_norm_static_fp8_quant = dummyFusionOp(
|
|
name="rms_norm_static_fp8_quant")
|
|
torch.ops._C.fused_add_rms_norm_static_fp8_quant = dummyFusionOp(
|
|
name="fused_add_rms_norm_static_fp8_quant")
|
|
torch.ops._C.rms_norm_dynamic_per_token_quant = dummyFusionOp(
|
|
name="rms_norm_dynamic_per_token_quant")
|