54668e73c5
### What this PR does / why we need it?
Initial version to support minimax-m2.5 on vllm-ascend.
This commit coverting original fp8 weight to a quantilized bf16 to
support Minimax-m2.5 on NPU.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
### Test Report
Self tested precision summary, where the official precision score of
AIME2025 is 86.3
<img width="426" height="84" alt="image"
src="https://github.com/user-attachments/assets/a3ce2452-92fa-4713-962e-862248e0b61a"
/>
---------
Signed-off-by: limuyuan <limuyuan3@huawei.com>
Signed-off-by: SparrowMu <52023119+SparrowMu@users.noreply.github.com>
Co-authored-by: limuyuan <limuyuan3@huawei.com>
46 lines
1.9 KiB
Python
46 lines
1.9 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
|
|
|
|
from vllm_ascend.utils import vllm_version_is
|
|
|
|
if HAS_TRITON:
|
|
import vllm_ascend.patch.worker.patch_triton
|
|
|
|
if not vllm_version_is("v0.16.0"):
|
|
import vllm_ascend.patch.worker.patch_qwen3_5 # noqa
|
|
|
|
# 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_minimax_m2 # noqa
|
|
import vllm_ascend.patch.worker.patch_minimax_m2_linear_attn # 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
|