Packages

erllama

0.6.2
0.8.0 retired 0.7.0 retired 0.6.2 retired 0.6.1 retired 0.6.0 retired 0.5.1 retired 0.5.0 retired 0.4.0 retired 0.3.0 retired 0.2.0 retired 0.1.2 retired 0.1.1 retired 0.1.0 retired

Native Erlang/OTP wrapper around llama.cpp with token-exact tiered KV cache; cache more warm state than fits in RAM

Retired package: Renamed - Renamed to barrel_inference: https://github.com/barrel-platform/barrel_inference
HexDocs

Current section

Files

Jump to
Readme
13 Versions
0 Dependencies
Dependants
Files
Activity
erllama c_src llama.cpp ggml include ggml-openvino.h
Raw

c_src/llama.cpp/ggml/include/ggml-openvino.h 

#pragma once



#include "ggml-backend.h"



#include <cstring>



#ifdef __cplusplus

extern "C" {

#endif



#define GGML_OPENVINO_NAME "OPENVINO"



// backend API

GGML_BACKEND_API ggml_backend_t ggml_backend_openvino_init(int device);



GGML_BACKEND_API bool ggml_backend_is_openvino(ggml_backend_t backend);



GGML_BACKEND_API bool ggml_backend_buffer_is_openvino(ggml_backend_buffer_t buffer);



GGML_BACKEND_API bool ggml_backend_buft_is_openvino(ggml_backend_buffer_type_t buft);



GGML_BACKEND_API bool ggml_backend_buft_is_openvino_host(ggml_backend_buffer_type_t buft);



GGML_BACKEND_API size_t ggml_backend_openvino_buffer_get_ctx_id(ggml_backend_buffer_t buffer);



// device buffer

GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_openvino_buffer_type(int device);



GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_openvino_host_buffer_type(int device);



GGML_BACKEND_API int ggml_backend_openvino_get_device_count(void);



GGML_BACKEND_API ggml_backend_reg_t ggml_backend_openvino_reg(void);



#ifdef __cplusplus

}

#endif