forked from triton-inference-server/core
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathensemble_model.h
60 lines (51 loc) · 2.5 KB
/
ensemble_model.h
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
// Copyright 2019-2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution.
// * Neither the name of NVIDIA CORPORATION nor the names of its
// contributors may be used to endorse or promote products derived
// from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#pragma once
#include "model.h"
#include "model_config.pb.h"
#include "scheduler.h"
#include "status.h"
namespace triton { namespace core {
class InferenceServer;
class EnsembleModel : public Model {
public:
EnsembleModel(EnsembleModel&&) = default;
static Status Create(
InferenceServer* server, const std::string& path, const int64_t version,
const inference::ModelConfig& model_config, const bool is_config_provided,
const double min_compute_capability, std::unique_ptr<Model>* model);
private:
DISALLOW_COPY_AND_ASSIGN(EnsembleModel);
explicit EnsembleModel(
const double min_compute_capability, const std::string& model_dir,
const int64_t version, const inference::ModelConfig& config)
: Model(min_compute_capability, model_dir, version, config)
{
}
friend std::ostream& operator<<(std::ostream&, const EnsembleModel&);
};
std::ostream& operator<<(std::ostream& out, const EnsembleModel& pb);
}} // namespace triton::core