cpuinfer.h 2.33 KB
Newer Older
chenxl's avatar
chenxl committed
1
/**
2
 * @Description  :
chenxl's avatar
chenxl committed
3
4
5
 * @Author       : chenht2022
 * @Date         : 2024-07-16 10:43:18
 * @Version      : 1.0.0
6
7
8
9
 * @LastEditors  : chenht2022
 * @LastEditTime : 2024-08-07 09:47:43
 * @Copyright (c) 2024 by KVCache.AI, All Rights Reserved.
 **/
Azure-Tang's avatar
Azure-Tang committed
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
 #ifndef CPUINFER_CPUINFER_H
 #define CPUINFER_CPUINFER_H
 
 #include <atomic>
 #include <condition_variable>
 #include <functional>
 #include <mutex>
 #include <queue>
 #include <thread>
 #include <vector>
 #ifdef KTRANSFORMERS_USE_CUDA
 #include "vendors/cuda.h"
 #elif KTRANSFORMERS_USE_MUSA
 #include "vendors/musa.h"
 #elif KTRANSFORMERS_USE_ROCM
 #define __HIP_PLATFORM_AMD__
 #include "vendors/hip.h"
 #endif
 
 #include "backend.h"
 #include "task_queue.h"
31
 #include "./vendors/vendor.h"
Azure-Tang's avatar
Azure-Tang committed
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
 
 #include "llama.cpp/ggml-impl.h"
 
 class CPUInfer {
    public:
     CPUInfer(int thread_num) {
         backend_ = new Backend(thread_num - 1);
         task_queue_ = new TaskQueue();
         for (int i = 0; i < (1 << 16); ++i) {
             ggml_table_f32_f16[i] = GGML_COMPUTE_FP16_TO_FP32(i);
         }
     }
 
     ~CPUInfer() {
         delete backend_;
         delete task_queue_;
     }
 
     template <typename Func, typename Obj, typename... Args>
     void enqueue(Func f, Obj* obj, Args... args) {
         task_queue_->enqueue([=]() {
             std::invoke(f, *obj, args..., backend_);
         });
     }
 
     void submit(std::pair<intptr_t, intptr_t> params) {
         void (*func)(void*) = (void (*)(void*))params.first;
         void* args = (void*)params.second;
         *((CPUInfer**)args) = this;
         func(args);
     }
 
     void sync() {
         task_queue_->sync();
     }
 
     void submit_with_cuda_stream(intptr_t user_cuda_stream, std::pair<intptr_t, intptr_t> params) {
         void (*func)(void*) = (void (*)(void*))params.first;
         void* args = (void*)params.second;
         *((CPUInfer**)args) = this;
         cudaLaunchHostFunc((cudaStream_t)user_cuda_stream, (cudaHostFn_t)func, args);
     }
 
     static void sync_(void* cpu_infer_ptr) {
         CPUInfer* cpuinfer = (CPUInfer*)cpu_infer_ptr;
         cpuinfer->sync();
     }
 
     void sync_with_cuda_stream(intptr_t user_cuda_stream) {
         cudaLaunchHostFunc((cudaStream_t)user_cuda_stream, (cudaHostFn_t)&sync_, (void*)this);
     }
 
    public:
     Backend* backend_;
     TaskQueue* task_queue_;
 };
 
 #endif