tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-26 10:09:41 -04:00
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

16
ggml/src/ggml-cpu/amx/mmq.h Normal file
View File

@@ -0,0 +1,16 @@
#pragma once
#include "common.h"
#ifdef __cplusplus
extern "C" {
#endif
size_t ggml_backend_amx_get_alloc_size(const struct ggml_tensor * tensor);
void ggml_backend_amx_convert_weight(struct ggml_tensor * tensor, const void * data, size_t offset, size_t size);
void ggml_backend_amx_mul_mat(const struct ggml_compute_params * params, struct ggml_tensor * dst);
#ifdef __cplusplus
}
#endif