mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 10:54:36 +00:00
60ce97c9d8
add intel amx isa detection add vnni kernel for gemv cases add vnni and amx kernel support for block_q8_0 code cleanup fix packing B issue enable openmp fine tune amx kernel switch to aten parallel pattern add error message for nested parallelism code cleanup add f16 support in ggml-amx add amx kernels for QK_K quant formats: Q4_K, Q5_K, Q6_K and IQ4_XS update CMakeList update README fix some compilation warning fix compiler warning when amx is not enabled minor change ggml-ci move ggml_amx_init from ggml.c to ggml-amx/mmq.cpp ggml-ci update CMakeLists with -mamx-tile, -mamx-int8 and -mamx-bf16 ggml-ci add amx as an ggml-backend update header file, the old path for immintrin.h has changed to ggml-cpu-impl.h minor change update CMakeLists.txt minor change apply weight prepacking in set_tensor method in ggml-backend fix compile error ggml-ci minor change ggml-ci update CMakeLists.txt ggml-ci add march dependency minor change ggml-ci change ggml_backend_buffer_is_host to return false for amx backend ggml-ci fix supports_op use device reg for AMX backend ggml-ci minor change ggml-ci minor change fix rebase set .buffer_from_host_ptr to be false for AMX backend
26 lines
498 B
C
26 lines
498 B
C
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
// buffer_type API
|
|
GGML_API ggml_backend_buffer_type_t ggml_backend_amx_buffer_type(void);
|
|
|
|
GGML_API bool ggml_backend_is_amx(ggml_backend_t backend);
|
|
|
|
// backend API
|
|
GGML_API ggml_backend_t ggml_backend_amx_init(void);
|
|
|
|
GGML_API void ggml_backend_amx_set_n_threads(ggml_backend_t backend_amx, int n_threads);
|
|
|
|
GGML_API ggml_backend_reg_t ggml_backend_amx_reg(void);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|