mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-17 21:51:27 -04:00
19d8762ab6
* rename ggml-cpu-aarch64.c to .cpp
* reformat extra cpu backend.
- clean Q4_0_N_M and IQ4_0_N_M
- remove from "file" tensor type
- allow only with dynamic repack
- extract cpu extra bufts and convert to C++
- hbm
- "aarch64"
- more generic use of extra buffer
- generalise extra_supports_op
- new API for "cpu-accel":
- amx
- aarch64
* clang-format
* Clean Q4_0_N_M ref
Enable restrict on C++
* add op GGML_OP_MUL_MAT_ID for Q4_0_N_M with runtime repack
* added/corrected control on tensor size for Q4 repacking.
* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* add debug logs on repacks.
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
11 lines
397 B
C
11 lines
397 B
C
#pragma once
|
|
#include "common.h"
|
|
|
|
size_t ggml_backend_amx_desired_wsize(const struct ggml_tensor * dst);
|
|
|
|
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);
|