mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
15771072c7
* RPC support multiple devices * rpc : update documentation (#16441) Update the README file to match the newly added functionality of exposing multiple devices from a single server. Co-authored-by: Diego Devesa <slarengh@gmail.com> # Conflicts: # examples/rpc/README.md * Remove memory settings * 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. * Add -cpu to include cpu backend --------- Co-authored-by: firecoperana <firecoperana> Co-authored-by: Radoslav Gerganov <rgerganov@gmail.com>
30 lines
976 B
C
30 lines
976 B
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 1
|
|
#define GGML_RPC_MAX_SERVERS 16
|
|
|
|
// backend API
|
|
GGML_API GGML_CALL ggml_backend_t ggml_backend_rpc_init(const char * endpoint, uint32_t device);
|
|
GGML_API GGML_CALL bool ggml_backend_is_rpc(ggml_backend_t backend);
|
|
|
|
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint, uint32_t device);
|
|
|
|
GGML_API GGML_CALL uint32_t ggml_backend_rpc_get_device_count(const char* endpoint);
|
|
|
|
GGML_API GGML_CALL void ggml_backend_rpc_get_device_memory(const char * endpoint, uint32_t device, size_t * free, size_t * total);
|
|
|
|
GGML_API GGML_CALL void ggml_backend_rpc_start_server(const char * endpoint, const char* cache_dir, size_t device, ggml_backend_t * devices, size_t* free_mem, size_t* total_mem);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|