Files
llama.cpp/ggml/include/ggml-rpc.h
T
Radoslav Gerganov 15d2b46b4d rpc : cache and reuse compute graphs (#15405)
Store the last computed graph and reuse it when possible.
Also do not return response from GRAPH_COMPUTE and assume it always
completes successfully. If this this is not the case, the server closes
the connection. This saves us a network round trip to the server.
2025-11-28 08:33:51 +00:00

32 lines
1.0 KiB
C

#pragma once
#include "ggml.h"
#include "ggml-backend.h"
#ifdef __cplusplus
extern "C" {
#endif
#define RPC_PROTO_MAJOR_VERSION 3
#define RPC_PROTO_MINOR_VERSION 5
#define RPC_PROTO_PATCH_VERSION 0
#define GGML_RPC_MAX_SERVERS 16
// backend API
GGML_BACKEND_API ggml_backend_t ggml_backend_rpc_init(const char * endpoint, uint32_t device);
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, uint32_t device);
GGML_BACKEND_API void ggml_backend_rpc_get_device_memory(const char * endpoint, uint32_t device, size_t * free, size_t * total);
GGML_BACKEND_API void ggml_backend_rpc_start_server(const char * endpoint, const char * cache_dir,
size_t n_threads, size_t n_devices, ggml_backend_dev_t * devices);
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_rpc_reg(void);
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_rpc_add_server(const char * endpoint);
#ifdef __cplusplus
}
#endif