forked from triton-inference-server/python_backend
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathrequest_executor.h
More file actions
56 lines (47 loc) · 2.31 KB
/
Copy pathrequest_executor.h
File metadata and controls
56 lines (47 loc) · 2.31 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
// Copyright 2021-2023, 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 <memory>
#include "infer_payload.h"
#include "infer_request.h"
#include "infer_response.h"
namespace triton { namespace backend { namespace python {
TRITONSERVER_Error* CreateTritonErrorFromException(
const PythonBackendException& pb_exception);
class RequestExecutor {
TRITONSERVER_ResponseAllocator* response_allocator_ = nullptr;
TRITONSERVER_Server* server_;
std::unique_ptr<SharedMemoryManager>& shm_pool_;
public:
std::future<std::unique_ptr<InferResponse>> Infer(
std::shared_ptr<InferRequest>& infer_request,
std::shared_ptr<InferPayload>& infer_payload);
RequestExecutor(
std::unique_ptr<SharedMemoryManager>& shm_pool,
TRITONSERVER_Server* server);
~RequestExecutor();
};
}}} // namespace triton::backend::python