mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-04-12 05:18:54 +02:00
7b8090810e
* rpc : send hash when tensor data is above some fixed threshold ref #10095 * rpc : put cache under $HOME/.cache/llama.cpp * try to fix win32 build * another try to fix win32 build * remove llama as dependency
31 lines
958 B
C
31 lines
958 B
C
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define GGML_RPC_MAX_SERVERS 16
|
|
|
|
// backend API
|
|
GGML_BACKEND_API ggml_backend_t ggml_backend_rpc_init(const char * endpoint);
|
|
GGML_BACKEND_API bool ggml_backend_is_rpc(ggml_backend_t backend);
|
|
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint);
|
|
|
|
GGML_BACKEND_API void ggml_backend_rpc_get_device_memory(const char * endpoint, size_t * free, size_t * total);
|
|
|
|
GGML_BACKEND_API void ggml_backend_rpc_start_server(ggml_backend_t backend, const char * endpoint,
|
|
const char * cache_dir,
|
|
size_t free_mem, size_t total_mem);
|
|
|
|
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_rpc_reg(void);
|
|
|
|
GGML_BACKEND_API ggml_backend_dev_t ggml_backend_rpc_add_device(const char * endpoint);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|