ee0f50e68f
* [Feature] support deepseek v3/r1/v3.2 * fix gpt_oss * update readme * update readme --------- Co-authored-by: hanhaowen <hanhaowen@baidu.com>
27 lines
1.1 KiB
Python
27 lines
1.1 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.rotary_embedding
|
|
import vllm_kunlun.ops.layernorm
|
|
import vllm_kunlun.ops.quantization.awq
|
|
import vllm_kunlun.ops.quantization.gptq
|
|
import vllm_kunlun.ops.vocab_parallel_embedding
|
|
import vllm_kunlun.ops.linear
|
|
import vllm_kunlun.ops.quantization.kernels.scaled_mm.cutlass
|
|
import vllm_kunlun.ops.vocab_parallel_embedding
|
|
import vllm_kunlun.ops.quantization.compressed_tensors_moe
|
|
import vllm_kunlun.ops.fused_moe.layer |