1ffca8673f
### What this PR does / why we need it?
Add basic 310p support. Only dense models work with eager mode now.
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
---------
Signed-off-by: Tflowers-0129 <2906339855@qq.com>
Signed-off-by: Shaoxu Cheng <2906339855@qq.com>
41 lines
1.3 KiB
Python
41 lines
1.3 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.
|
|
#
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import torch
|
|
from vllm.config import VllmConfig
|
|
from vllm.v1.kv_cache_interface import AttentionSpec
|
|
|
|
from vllm_ascend._310p.attention.attention_mask import AttentionMaskBuilder
|
|
from vllm_ascend.attention.attention_v1 import AscendAttentionMetadataBuilder as _BaseBuilder
|
|
|
|
|
|
class AscendAttentionMetadataBuilder310P(_BaseBuilder):
|
|
def __init__(
|
|
self,
|
|
kv_cache_spec: AttentionSpec,
|
|
layer_names: list[str],
|
|
vllm_config: VllmConfig,
|
|
device: torch.device,
|
|
):
|
|
super().__init__(kv_cache_spec, layer_names, vllm_config, device)
|
|
|
|
self.attn_mask_builder: Any = AttentionMaskBuilder(self.device)
|