diff options
Diffstat (limited to 'llama.cpp/ggml/include/ggml-rpc.h')
| -rw-r--r-- | llama.cpp/ggml/include/ggml-rpc.h | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/llama.cpp/ggml/include/ggml-rpc.h b/llama.cpp/ggml/include/ggml-rpc.h new file mode 100644 index 0000000..df1ad2a --- /dev/null +++ b/llama.cpp/ggml/include/ggml-rpc.h @@ -0,0 +1,30 @@ +#pragma once + +#include "ggml-backend.h" + +#ifdef __cplusplus +extern "C" { +#endif + +#define RPC_PROTO_MAJOR_VERSION 3 +#define RPC_PROTO_MINOR_VERSION 6 +#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 |
