tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : move AMX to the CPU backend (#10570)

Browse Source 
* ggml : move AMX to the CPU backend

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Diego Devesa
2024-11-29 21:54:58 +01:00
committed by GitHub
parent b782e5c7d4
commit 7cc2d2c889
64 changed files with 514 additions and 801 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
ggml/include/ggml-amx.h
View File

@ -1,25 +0,0 @@
#pragma once
#include "ggml.h"
#include "ggml-backend.h"
#ifdef __cplusplus
extern "C" {
#endif
// buffer_type API
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_amx_buffer_type(void);
GGML_BACKEND_API bool ggml_backend_is_amx(ggml_backend_t backend);
// backend API
GGML_BACKEND_API ggml_backend_t ggml_backend_amx_init(void);
GGML_BACKEND_API void ggml_backend_amx_set_n_threads(ggml_backend_t backend_amx, int n_threads);
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_amx_reg(void);
#ifdef __cplusplus
}
#endif