mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-04 18:21:52 +08:00
6f07fa81d7
Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com> KVCacheManagerV2 is a new python-based implementation of the KV cache manager, featuring cleaner API, better abstraction and better code quality without the accumulated legacy.
32 lines
998 B
C++
32 lines
998 B
C++
/*
|
|
* SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
* SPDX-License-Identifier: Apache-2.0
|
|
*
|
|
* 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.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <nanobind/nanobind.h>
|
|
|
|
namespace nb = nanobind;
|
|
|
|
namespace tensorrt_llm::batch_manager::kv_cache_manager_v2
|
|
{
|
|
class KVCacheManagerV2UtilsBindings
|
|
{
|
|
public:
|
|
static void initBindings(nb::module_& module);
|
|
};
|
|
} // namespace tensorrt_llm::batch_manager::kv_cache_manager_v2
|