6f30bc439d
* Add MTP support in eagle.py Signed-off-by: wanghao129 <wanghao129@baidu.com> * new pr for mtp Signed-off-by: wanghao129 <wanghao129@baidu.com> * Revert formatting changes in deepseek_v2.py Signed-off-by: wanghao129 <wanghao129@baidu.com> --------- Signed-off-by: wanghao129 <wanghao129@baidu.com> Co-authored-by: wanghao129 <wanghao129@baidu.com>
37 lines
1.3 KiB
Python
37 lines
1.3 KiB
Python
#
|
|
# Copyright (c) 2025 Baidu, Inc. 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 vllm_kunlun.ops.fused_moe.layer
|
|
|
|
# base layers
|
|
import vllm_kunlun.ops.layernorm
|
|
import vllm_kunlun.ops.linear
|
|
|
|
# quantization
|
|
import vllm_kunlun.ops.quantization.awq
|
|
import vllm_kunlun.ops.quantization.compressed_tensors.compressed_tensors
|
|
import vllm_kunlun.ops.quantization.compressed_tensors.compressed_tensors_moe
|
|
import vllm_kunlun.ops.quantization.gptq
|
|
import vllm_kunlun.ops.quantization.kernels.kunlun_exllama_linear
|
|
import vllm_kunlun.ops.quantization.kernels.kunlun_scale_mm
|
|
import vllm_kunlun.ops.quantization.moe_wna16
|
|
|
|
# embedding
|
|
import vllm_kunlun.ops.rotary_embedding
|
|
import vllm_kunlun.ops.vocab_parallel_embedding
|
|
import vllm_kunlun.v1.sample.spec_decode.eagle
|