mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-11 10:36:54 +00:00
f470bc36be
* move ggml-cpu-aarch64 to repack * split quantize_row_q8_0/1 * split helper functions * split ggml_vec_dot_q4_0_q8_0 * split ggml_vec_dot_q4_1_q8_1 * split ggml_vec_dot_q5_0_q8_0 * split ggml_vec_dot_q5_1_q8_1 * split ggml_vec_dot_q8_0_q8_0 * split ggml_vec_dot_tq1_0_q8_K * split ggml_vec_dot_tq2_0_q8_K * split ggml_vec_dot_q2_K_q8_K * split ggml_vec_dot_q3_K_q8_K * split ggml_vec_dot_q4_K_q8_K * split ggml_vec_dot_q5_K_q8_K * split ggml_vec_dot_q6_K_q8_K * split ggml_vec_dot_iq2_xxs_q8_K * split ggml_vec_dot_iq2_xs_q8_K * split ggml_vec_dot_iq2_s_q8_K * split ggml_vec_dot_iq3_xxs_q8_K * split ggml_vec_dot_iq3_s_q8_K * split ggml_vec_dot_iq1_s_q8_K * split ggml_vec_dot_iq1_m_q8_K * split ggml_vec_dot_iq4_nl_q8_0 * split ggml_vec_dot_iq4_xs_q8_K * fix typos * fix missing prototypes * rename ggml-cpu-quants.c * rename ggml-cpu-traits * rename arm folder * move cpu-feats-x86.cpp * rename ggml-cpu-hbm * update arm detection macro in quants.c * move iq quant tables * split ggml_quantize_mat_q8_0/K * split ggml_gemv_* * split ggml_gemm_* * rename namespace aarch64 to repack * use weak aliases to replace test macros * rename GGML_CPU_AARCH64 to GGML_CPU_REPACK * rename more aarch64 to repack * clean up rebase leftover * fix compilation errors * remove trailing spaces * try to fix clang compilation errors * try to fix clang compilation errors again * try to fix clang compilation errors, 3rd attempt * try to fix clang compilation errors, 4th attempt * try to fix clang compilation errors, 5th attempt * try to fix clang compilation errors, 6th attempt * try to fix clang compilation errors, 7th attempt * try to fix clang compilation errors, 8th attempt * try to fix clang compilation errors, 9th attempt * more cleanup * fix compilation errors * fix apple targets * fix a typo in arm version of ggml_vec_dot_q4_K_q8_K Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
39 lines
1.1 KiB
C++
39 lines
1.1 KiB
C++
#pragma once
|
|
#include "ggml-backend-impl.h"
|
|
#include "ggml-cpu-impl.h"
|
|
#include "ggml.h"
|
|
|
|
#ifdef __cplusplus
|
|
# include <vector>
|
|
extern "C" {
|
|
#endif
|
|
|
|
// return true if op part of extra "accelerator"
|
|
bool ggml_cpu_extra_compute_forward(struct ggml_compute_params * params, struct ggml_tensor * op);
|
|
bool ggml_cpu_extra_work_size(int n_threads, const struct ggml_tensor * op, size_t * size);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
|
|
namespace ggml::cpu {
|
|
// register in tensor->extra
|
|
class tensor_traits {
|
|
public:
|
|
virtual ~tensor_traits();
|
|
virtual bool work_size(int n_threads, const struct ggml_tensor * op, size_t & size) = 0;
|
|
virtual bool compute_forward(struct ggml_compute_params * params, struct ggml_tensor * op) = 0;
|
|
};
|
|
|
|
class extra_buffer_type {
|
|
public:
|
|
virtual ~extra_buffer_type();
|
|
virtual bool supports_op(ggml_backend_dev_t dev, const struct ggml_tensor * op) = 0;
|
|
virtual tensor_traits * get_tensor_traits(const struct ggml_tensor * op) = 0;
|
|
};
|
|
} // namespace ggml::cpu
|
|
|
|
// implemented in ggml-cpu.cpp.
|
|
std::vector<ggml_backend_buffer_type_t> & ggml_backend_cpu_get_extra_buffers_type();
|
|
|
|
#endif
|