-
Notifications
You must be signed in to change notification settings - Fork 2.5k
Expand file tree
/
Copy pathschedulerConfig.cpp
More file actions
60 lines (51 loc) · 2.12 KB
/
Copy pathschedulerConfig.cpp
File metadata and controls
60 lines (51 loc) · 2.12 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
/*
* SPDX-FileCopyrightText: Copyright (c) 2025-2026 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.
*/
#include "tensorrt_llm/executor/executor.h"
namespace tensorrt_llm::executor
{
SchedulerConfig::SchedulerConfig(CapacitySchedulerPolicy capacitySchedulerPolicy,
std::optional<ContextChunkingPolicy> contextChunkingPolicy, std::optional<DynamicBatchConfig> dynamicBatchConfig,
bool enablePrefixAwareScheduling)
: mCapacitySchedulerPolicy(capacitySchedulerPolicy)
, mContextChunkingPolicy(std::move(contextChunkingPolicy))
, mDynamicBatchConfig(std::move(dynamicBatchConfig))
, mEnablePrefixAwareScheduling(enablePrefixAwareScheduling)
{
}
bool SchedulerConfig::operator==(SchedulerConfig const& other) const
{
return mCapacitySchedulerPolicy == other.mCapacitySchedulerPolicy
&& mContextChunkingPolicy == other.mContextChunkingPolicy && mDynamicBatchConfig == other.mDynamicBatchConfig
&& mEnablePrefixAwareScheduling == other.mEnablePrefixAwareScheduling;
}
[[nodiscard]] CapacitySchedulerPolicy SchedulerConfig::getCapacitySchedulerPolicy() const
{
return mCapacitySchedulerPolicy;
}
[[nodiscard]] std::optional<ContextChunkingPolicy> SchedulerConfig::getContextChunkingPolicy() const
{
return mContextChunkingPolicy;
}
[[nodiscard]] std::optional<DynamicBatchConfig> SchedulerConfig::getDynamicBatchConfig() const
{
return mDynamicBatchConfig;
}
[[nodiscard]] bool SchedulerConfig::getEnablePrefixAwareScheduling() const
{
return mEnablePrefixAwareScheduling;
}
} // namespace tensorrt_llm::executor