Files
xc-llm-ascend/vllm_ascend/patch/worker/__init__.py
drslark 6a7115fa0d [main][feature] Support quarot for eagle3 without embedding (#7038)
### What this PR does / why we need it?
If some `eagle3` model without embed_tokens works with `quarot` target
model, the acceptence rate will drop.
We solve it in this PR.
The relative vllm pr is https://github.com/vllm-project/vllm/pull/36225.

- vLLM main:
4034c3d32e

Signed-off-by: drslark <slarksblood@qq.com>
2026-03-09 10:43:06 +08:00

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.
#
from vllm.triton_utils import HAS_TRITON
if HAS_TRITON:
import vllm_ascend.patch.worker.patch_triton
# isort: off
import vllm_ascend.patch.platform.patch_sched_yield # noqa
import vllm_ascend.patch.worker.patch_unquantized_gemm # noqa
import vllm_ascend.patch.worker.patch_bert # noqa
import vllm_ascend.patch.worker.patch_distributed # noqa
import vllm_ascend.patch.worker.patch_multimodal_merge # noqa
import vllm_ascend.patch.worker.patch_qwen3_next # noqa
import vllm_ascend.patch.worker.patch_qwen3_next_mtp # noqa
import vllm_ascend.patch.worker.patch_rejection_sampler # noqa
import vllm_ascend.patch.worker.patch_v2_eagle # noqa
import vllm_ascend.patch.worker.patch_v2_uva # noqa
import vllm_ascend.patch.worker.patch_huanyuan_vl # noqa
import vllm_ascend.patch.worker.patch_routed_experts_capturer # noqa
import vllm_ascend.patch.worker.patch_npugraph_ex_triton # noqa
import vllm_ascend.patch.worker.patch_kimi_k25 # noqa
import vllm_ascend.patch.worker.patch_draft_quarot # noqa