e7e1a7dc05
### What this PR does / why we need it?
#5051 only implement a basic framework for model runner v2, but there
are still some bugs for e2e functionality, this PR aim to enable basic
functionality.
model runner v2 plans:
https://github.com/vllm-project/vllm-ascend/issues/5208
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
57 lines
1.9 KiB
Python
57 lines
1.9 KiB
Python
# Adapt from https://github.com/vllm-project/vllm/blob/main/vllm/v1/worker/gpu/input_batch.py
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
# 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.
|
|
#
|
|
|
|
import numpy as np
|
|
import torch
|
|
from vllm.v1.worker.gpu.input_batch import InputBuffers
|
|
|
|
|
|
class AscendInputBuffers(InputBuffers):
|
|
"""Input buffers for Ascend NPUs."""
|
|
|
|
def __init__(
|
|
self,
|
|
max_num_reqs: int,
|
|
max_num_tokens: int,
|
|
inputs_embeds_size: int,
|
|
vocab_size: int,
|
|
dtype: torch.dtype,
|
|
device: torch.device,
|
|
pin_memory: bool,
|
|
):
|
|
super().__init__(
|
|
max_num_reqs,
|
|
max_num_tokens,
|
|
inputs_embeds_size,
|
|
vocab_size,
|
|
dtype,
|
|
device,
|
|
pin_memory,
|
|
)
|
|
# Create seq_lens_cpu and seq_lens_np.
|
|
# npu's attention backend still needs seq_lens on CPU side.
|
|
self.seq_lens_cpu: torch.Tensor = torch.zeros(
|
|
max_num_reqs,
|
|
dtype=torch.int32,
|
|
device="cpu",
|
|
)
|
|
# seq_len_np and seq_lens_cpu share the same memory.
|
|
# define seq_lens_np for easier calculation with numpy.
|
|
self.seq_lens_np: np.ndarray = self.seq_lens_cpu.numpy()
|