c980e68d40
### What this PR does / why we need it?
This PR aims to support aclgraph for model runner v2, please see RFC
#5208. The PR contains these modifications:
- adapt to newest commit of vllm main branch.
- supply a unified interface of extra forward context for both model
runner v1 and model runner v2.
- implement graph mode for main model.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
59 lines
2.0 KiB
Python
59 lines
2.0 KiB
Python
# Adapt from https://github.com/vllm-project/vllm/blob/main/vllm/v1/worker/gpu/block_table.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 torch
|
|
from vllm.v1.worker.gpu.block_table import BlockTables
|
|
|
|
|
|
class AscendBlockTables(BlockTables):
|
|
"""Block table for Ascend NPUs."""
|
|
|
|
def __init__(
|
|
self,
|
|
block_sizes: list[int],
|
|
max_num_reqs: int,
|
|
max_num_batched_tokens: int,
|
|
max_model_len: int,
|
|
device: torch.device,
|
|
cp_size: int = 1,
|
|
cp_rank: int = 0,
|
|
cp_interleave: int = 1,
|
|
):
|
|
super().__init__(
|
|
block_sizes,
|
|
max_num_reqs,
|
|
max_num_batched_tokens,
|
|
max_model_len,
|
|
device,
|
|
cp_size,
|
|
cp_rank,
|
|
cp_interleave,
|
|
)
|
|
# because we will override these attribute, delete these attribute to
|
|
# make sure it's collected by python gc immediately.
|
|
del self.slot_mappings
|
|
# vllm-ascend' reshape_and_cache function requires slot_mappings to be int32.
|
|
# so we need to redefine slot_mappings to be int32.
|
|
self.slot_mappings: torch.Tensor = torch.zeros(
|
|
self.num_kv_cache_groups,
|
|
self.max_num_batched_tokens,
|
|
dtype=torch.int32,
|
|
device=self.device,
|
|
)
|