mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-30 08:42:00 +00:00
ggml-cpu : rework weak alias on apple targets (#14146)
* ggml-cpu : rework weak alias on apple targets * fix powerpc detection * fix ppc detection * fix powerpc detection on darwin
This commit is contained in:
xctan
@@ -36,8 +36,7 @@ function(ggml_get_system_arch)
|
||||
(NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND
|
||||
CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|i686|AMD64|amd64)$"))
|
||||
set(GGML_SYSTEM_ARCH "x86" PARENT_SCOPE)
|
||||
elseif ("${CMAKE_SYSTEM_PROCESSOR} " STREQUAL "ppc64le " OR
|
||||
"${CMAKE_SYSTEM_PROCESSOR} " STREQUAL "powerpc ")
|
||||
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc|power")
|
||||
set(GGML_SYSTEM_ARCH "PowerPC" PARENT_SCOPE)
|
||||
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
|
||||
set(GGML_SYSTEM_ARCH "loongarch64" PARENT_SCOPE)
|
||||
|
||||
88
ggml/src/ggml-cpu/apple-fallback.h
Normal file
88
ggml/src/ggml-cpu/apple-fallback.h
Normal file
@@ -0,0 +1,88 @@
|
||||
#pragma once
|
||||
|
||||
// Solve alias issue for Apple targets (currently PowerPC, x86, and ARM64).
|
||||
// Mach-O has a weak alias equivalent but no practical compiler support can
|
||||
// be found, so we need to do it manually.
|
||||
// ref: https://stackoverflow.com/questions/42757744
|
||||
//
|
||||
// This file is a complement to native implementations in the `arch` folder.
|
||||
// A kernel in quants.c or repack.cpp is either:
|
||||
// - implemented in the `arch` folder, or
|
||||
// - defined in this file to remove the `_generic` suffix
|
||||
|
||||
#if defined(GGML_CPU_GENERIC)
|
||||
// quants.c
|
||||
#define quantize_row_q8_0_generic quantize_row_q8_0
|
||||
#define quantize_row_q8_1_generic quantize_row_q8_1
|
||||
#define quantize_row_q8_K_generic quantize_row_q8_K
|
||||
#define ggml_vec_dot_q4_0_q8_0_generic ggml_vec_dot_q4_0_q8_0
|
||||
#define ggml_vec_dot_q4_1_q8_1_generic ggml_vec_dot_q4_1_q8_1
|
||||
#define ggml_vec_dot_q5_0_q8_0_generic ggml_vec_dot_q5_0_q8_0
|
||||
#define ggml_vec_dot_q5_1_q8_1_generic ggml_vec_dot_q5_1_q8_1
|
||||
#define ggml_vec_dot_q8_0_q8_0_generic ggml_vec_dot_q8_0_q8_0
|
||||
#define ggml_vec_dot_tq1_0_q8_K_generic ggml_vec_dot_tq1_0_q8_K
|
||||
#define ggml_vec_dot_tq2_0_q8_K_generic ggml_vec_dot_tq2_0_q8_K
|
||||
#define ggml_vec_dot_q2_K_q8_K_generic ggml_vec_dot_q2_K_q8_K
|
||||
#define ggml_vec_dot_q3_K_q8_K_generic ggml_vec_dot_q3_K_q8_K
|
||||
#define ggml_vec_dot_q4_K_q8_K_generic ggml_vec_dot_q4_K_q8_K
|
||||
#define ggml_vec_dot_q5_K_q8_K_generic ggml_vec_dot_q5_K_q8_K
|
||||
#define ggml_vec_dot_q6_K_q8_K_generic ggml_vec_dot_q6_K_q8_K
|
||||
#define ggml_vec_dot_iq2_xxs_q8_K_generic ggml_vec_dot_iq2_xxs_q8_K
|
||||
#define ggml_vec_dot_iq2_xs_q8_K_generic ggml_vec_dot_iq2_xs_q8_K
|
||||
#define ggml_vec_dot_iq2_s_q8_K_generic ggml_vec_dot_iq2_s_q8_K
|
||||
#define ggml_vec_dot_iq3_xxs_q8_K_generic ggml_vec_dot_iq3_xxs_q8_K
|
||||
#define ggml_vec_dot_iq3_s_q8_K_generic ggml_vec_dot_iq3_s_q8_K
|
||||
#define ggml_vec_dot_iq1_s_q8_K_generic ggml_vec_dot_iq1_s_q8_K
|
||||
#define ggml_vec_dot_iq1_m_q8_K_generic ggml_vec_dot_iq1_m_q8_K
|
||||
#define ggml_vec_dot_iq4_nl_q8_0_generic ggml_vec_dot_iq4_nl_q8_0
|
||||
#define ggml_vec_dot_iq4_xs_q8_K_generic ggml_vec_dot_iq4_xs_q8_K
|
||||
// repack.cpp
|
||||
#define ggml_quantize_mat_q8_0_4x4_generic ggml_quantize_mat_q8_0_4x4
|
||||
#define ggml_quantize_mat_q8_0_4x8_generic ggml_quantize_mat_q8_0_4x8
|
||||
#define ggml_quantize_mat_q8_K_4x8_generic ggml_quantize_mat_q8_K_4x8
|
||||
#define ggml_gemv_q4_0_4x4_q8_0_generic ggml_gemv_q4_0_4x4_q8_0
|
||||
#define ggml_gemv_q4_0_4x8_q8_0_generic ggml_gemv_q4_0_4x8_q8_0
|
||||
#define ggml_gemv_q4_0_8x8_q8_0_generic ggml_gemv_q4_0_8x8_q8_0
|
||||
#define ggml_gemv_q4_K_8x8_q8_K_generic ggml_gemv_q4_K_8x8_q8_K
|
||||
#define ggml_gemv_iq4_nl_4x4_q8_0_generic ggml_gemv_iq4_nl_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x4_q8_0_generic ggml_gemm_q4_0_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x8_q8_0_generic ggml_gemm_q4_0_4x8_q8_0
|
||||
#define ggml_gemm_q4_0_8x8_q8_0_generic ggml_gemm_q4_0_8x8_q8_0
|
||||
#define ggml_gemm_q4_K_8x8_q8_K_generic ggml_gemm_q4_K_8x8_q8_K
|
||||
#define ggml_gemm_iq4_nl_4x4_q8_0_generic ggml_gemm_iq4_nl_4x4_q8_0
|
||||
#elif defined(__aarch64__) || defined(__arm__)
|
||||
// repack.cpp
|
||||
#define ggml_quantize_mat_q8_K_4x8_generic ggml_quantize_mat_q8_K_4x8
|
||||
#define ggml_gemv_q4_K_8x8_q8_K_generic ggml_gemv_q4_K_8x8_q8_K
|
||||
#define ggml_gemm_q4_K_8x8_q8_K_generic ggml_gemm_q4_K_8x8_q8_K
|
||||
#elif defined(__x86_64__) || defined(__i386__)
|
||||
// repack.cpp
|
||||
#define ggml_quantize_mat_q8_0_4x4_generic ggml_quantize_mat_q8_0_4x4
|
||||
#define ggml_gemv_q4_0_4x4_q8_0_generic ggml_gemv_q4_0_4x4_q8_0
|
||||
#define ggml_gemv_q4_0_4x8_q8_0_generic ggml_gemv_q4_0_4x8_q8_0
|
||||
#define ggml_gemv_iq4_nl_4x4_q8_0_generic ggml_gemv_iq4_nl_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x4_q8_0_generic ggml_gemm_q4_0_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x8_q8_0_generic ggml_gemm_q4_0_4x8_q8_0
|
||||
#define ggml_gemm_iq4_nl_4x4_q8_0_generic ggml_gemm_iq4_nl_4x4_q8_0
|
||||
#elif defined(__POWERPC__)
|
||||
// ref: https://github.com/ggml-org/llama.cpp/pull/14146#issuecomment-2972561679
|
||||
// quants.c
|
||||
#define quantize_row_q8_K_generic quantize_row_q8_K
|
||||
#define ggml_vec_dot_tq1_0_q8_K_generic ggml_vec_dot_tq1_0_q8_K
|
||||
#define ggml_vec_dot_tq2_0_q8_K_generic ggml_vec_dot_tq2_0_q8_K
|
||||
#define ggml_vec_dot_iq1_m_q8_K_generic ggml_vec_dot_iq1_m_q8_K
|
||||
// repack.cpp
|
||||
#define ggml_quantize_mat_q8_0_4x4_generic ggml_quantize_mat_q8_0_4x4
|
||||
#define ggml_quantize_mat_q8_0_4x8_generic ggml_quantize_mat_q8_0_4x8
|
||||
#define ggml_quantize_mat_q8_K_4x8_generic ggml_quantize_mat_q8_K_4x8
|
||||
#define ggml_gemv_q4_0_4x4_q8_0_generic ggml_gemv_q4_0_4x4_q8_0
|
||||
#define ggml_gemv_q4_0_4x8_q8_0_generic ggml_gemv_q4_0_4x8_q8_0
|
||||
#define ggml_gemv_q4_0_8x8_q8_0_generic ggml_gemv_q4_0_8x8_q8_0
|
||||
#define ggml_gemv_q4_K_8x8_q8_K_generic ggml_gemv_q4_K_8x8_q8_K
|
||||
#define ggml_gemv_iq4_nl_4x4_q8_0_generic ggml_gemv_iq4_nl_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x4_q8_0_generic ggml_gemm_q4_0_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x8_q8_0_generic ggml_gemm_q4_0_4x8_q8_0
|
||||
#define ggml_gemm_q4_0_8x8_q8_0_generic ggml_gemm_q4_0_8x8_q8_0
|
||||
#define ggml_gemm_q4_K_8x8_q8_K_generic ggml_gemm_q4_K_8x8_q8_K
|
||||
#define ggml_gemm_iq4_nl_4x4_q8_0_generic ggml_gemm_iq4_nl_4x4_q8_0
|
||||
#endif
|
||||
@@ -509,7 +509,7 @@ void ggml_barrier(struct ggml_threadpool * tp);
|
||||
|
||||
#define GGML_DO_PRAGMA_(x) _Pragma (#x)
|
||||
#define GGML_DO_PRAGMA(x) GGML_DO_PRAGMA_(x)
|
||||
#if defined(GGML_CPU_GENERIC) || defined(__HIPCC__)
|
||||
#if defined(GGML_CPU_GENERIC) || defined(__HIPCC__) || defined(__APPLE__)
|
||||
// Note for Apple targets:
|
||||
// - clang: aliases are not supported on darwin
|
||||
// - all native kernels need to be implemented in both x86 and arm files
|
||||
|
||||
@@ -5,6 +5,10 @@
|
||||
#include "ggml-quants.h"
|
||||
#include "quants.h"
|
||||
|
||||
#if defined(__APPLE__)
|
||||
#include "apple-fallback.h"
|
||||
#endif
|
||||
|
||||
#include <string.h>
|
||||
#include <assert.h>
|
||||
#include <float.h>
|
||||
|
||||
@@ -84,33 +84,6 @@ void ggml_vec_dot_iq1_m_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs,
|
||||
void ggml_vec_dot_iq4_nl_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
|
||||
void ggml_vec_dot_iq4_xs_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
|
||||
|
||||
#if defined(GGML_CPU_GENERIC)
|
||||
#define quantize_row_q8_0_generic quantize_row_q8_0
|
||||
#define quantize_row_q8_1_generic quantize_row_q8_1
|
||||
#define quantize_row_q8_K_generic quantize_row_q8_K
|
||||
#define ggml_vec_dot_q4_0_q8_0_generic ggml_vec_dot_q4_0_q8_0
|
||||
#define ggml_vec_dot_q4_1_q8_1_generic ggml_vec_dot_q4_1_q8_1
|
||||
#define ggml_vec_dot_q5_0_q8_0_generic ggml_vec_dot_q5_0_q8_0
|
||||
#define ggml_vec_dot_q5_1_q8_1_generic ggml_vec_dot_q5_1_q8_1
|
||||
#define ggml_vec_dot_q8_0_q8_0_generic ggml_vec_dot_q8_0_q8_0
|
||||
#define ggml_vec_dot_tq1_0_q8_K_generic ggml_vec_dot_tq1_0_q8_K
|
||||
#define ggml_vec_dot_tq2_0_q8_K_generic ggml_vec_dot_tq2_0_q8_K
|
||||
#define ggml_vec_dot_q2_K_q8_K_generic ggml_vec_dot_q2_K_q8_K
|
||||
#define ggml_vec_dot_q3_K_q8_K_generic ggml_vec_dot_q3_K_q8_K
|
||||
#define ggml_vec_dot_q4_K_q8_K_generic ggml_vec_dot_q4_K_q8_K
|
||||
#define ggml_vec_dot_q5_K_q8_K_generic ggml_vec_dot_q5_K_q8_K
|
||||
#define ggml_vec_dot_q6_K_q8_K_generic ggml_vec_dot_q6_K_q8_K
|
||||
#define ggml_vec_dot_iq2_xxs_q8_K_generic ggml_vec_dot_iq2_xxs_q8_K
|
||||
#define ggml_vec_dot_iq2_xs_q8_K_generic ggml_vec_dot_iq2_xs_q8_K
|
||||
#define ggml_vec_dot_iq2_s_q8_K_generic ggml_vec_dot_iq2_s_q8_K
|
||||
#define ggml_vec_dot_iq3_xxs_q8_K_generic ggml_vec_dot_iq3_xxs_q8_K
|
||||
#define ggml_vec_dot_iq3_s_q8_K_generic ggml_vec_dot_iq3_s_q8_K
|
||||
#define ggml_vec_dot_iq1_s_q8_K_generic ggml_vec_dot_iq1_s_q8_K
|
||||
#define ggml_vec_dot_iq1_m_q8_K_generic ggml_vec_dot_iq1_m_q8_K
|
||||
#define ggml_vec_dot_iq4_nl_q8_0_generic ggml_vec_dot_iq4_nl_q8_0
|
||||
#define ggml_vec_dot_iq4_xs_q8_K_generic ggml_vec_dot_iq4_xs_q8_K
|
||||
#endif
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
@@ -8,6 +8,10 @@
|
||||
#include "ggml-cpu-impl.h"
|
||||
#include "traits.h"
|
||||
|
||||
#if defined(__APPLE__)
|
||||
#include "apple-fallback.h"
|
||||
#endif
|
||||
|
||||
#include <cmath>
|
||||
#include <cstring>
|
||||
#include <cassert>
|
||||
|
||||
@@ -67,7 +67,7 @@ extern "C" {
|
||||
// Workaround for clang:
|
||||
// clang++ complains: ``error: call to 'ggml_gemm_q4_0_4x4_q8_0' is ambiguous''
|
||||
// repro: https://godbolt.org/z/oKdeWKonM (ICE), https://godbolt.org/z/1szq6P36v (ambiguous call)
|
||||
#if defined(GGML_CPU_CLANG_WORKAROUND) || !(defined(__GNUC__) && defined(__clang__)) || defined(__HIPCC__)
|
||||
#if defined(GGML_CPU_CLANG_WORKAROUND) || defined(__APPLE__) || !(defined(__GNUC__) && defined(__clang__)) || defined(__HIPCC__)
|
||||
void ggml_quantize_mat_q8_0_4x4(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
|
||||
void ggml_quantize_mat_q8_0_4x8(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
|
||||
void ggml_quantize_mat_q8_K_4x8(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k);
|
||||
@@ -98,22 +98,6 @@ void ggml_gemm_q4_0_8x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs,
|
||||
void ggml_gemm_q4_K_8x8_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc);
|
||||
void ggml_gemm_iq4_nl_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc);
|
||||
|
||||
#if defined(GGML_CPU_GENERIC)
|
||||
#define ggml_quantize_mat_q8_0_4x4_generic ggml_quantize_mat_q8_0_4x4
|
||||
#define ggml_quantize_mat_q8_0_4x8_generic ggml_quantize_mat_q8_0_4x8
|
||||
#define ggml_quantize_mat_q8_K_4x8_generic ggml_quantize_mat_q8_K_4x8
|
||||
#define ggml_gemv_q4_0_4x4_q8_0_generic ggml_gemv_q4_0_4x4_q8_0
|
||||
#define ggml_gemv_q4_0_4x8_q8_0_generic ggml_gemv_q4_0_4x8_q8_0
|
||||
#define ggml_gemv_q4_0_8x8_q8_0_generic ggml_gemv_q4_0_8x8_q8_0
|
||||
#define ggml_gemv_q4_K_8x8_q8_K_generic ggml_gemv_q4_K_8x8_q8_K
|
||||
#define ggml_gemv_iq4_nl_4x4_q8_0_generic ggml_gemv_iq4_nl_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x4_q8_0_generic ggml_gemm_q4_0_4x4_q8_0
|
||||
#define ggml_gemm_q4_0_4x8_q8_0_generic ggml_gemm_q4_0_4x8_q8_0
|
||||
#define ggml_gemm_q4_0_8x8_q8_0_generic ggml_gemm_q4_0_8x8_q8_0
|
||||
#define ggml_gemm_q4_K_8x8_q8_K_generic ggml_gemm_q4_K_8x8_q8_K
|
||||
#define ggml_gemm_iq4_nl_4x4_q8_0_generic ggml_gemm_iq4_nl_4x4_q8_0
|
||||
#endif
|
||||
|
||||
#if defined(__cplusplus)
|
||||
} // extern "C"
|
||||
#endif
|
||||
|
||||
Reference in New Issue
Block a user