vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix error C2065: '__fp16': undeclared identifier

Browse source
This commit is contained in:
Michael Podvitskiy 2024-03-08 11:55:37 +01:00
parent 8dd390519b
commit 2498f6ad50
2 changed files with 8 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml-impl.h
View file

@ -53,26 +53,30 @@ extern "C" {
//
#include <arm_neon.h>
typedef __fp16 ggml_fp16_internal_t;
#define GGML_COMPUTE_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x)
#define GGML_COMPUTE_FP32_TO_FP16(x) ggml_compute_fp32_to_fp16(x)
#define GGML_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x)
static inline float ggml_compute_fp16_to_fp32(ggml_fp16_t h) {
__fp16 tmp;
ggml_fp16_internal_t tmp;
memcpy(&tmp, &h, sizeof(ggml_fp16_t));
return (float)tmp;
}
static inline ggml_fp16_t ggml_compute_fp32_to_fp16(float f) {
ggml_fp16_t res;
__fp16 tmp = f;
ggml_fp16_internal_t tmp = f;
memcpy(&res, &tmp, sizeof(ggml_fp16_t));
return res;
}
#else
typedef uint16_t ggml_fp16_internal_t;
#ifdef __wasm_simd128__
#include <wasm_simd128.h>
#else

4
ggml.c
View file

@ -857,7 +857,7 @@ inline static float vaddvq_f32(float32x4_t v) {
#define GGML_F16x8 float16x8_t
#define GGML_F16x8_ZERO vdupq_n_f16(0.0f)
#define GGML_F16x8_SET1(x) vdupq_n_f16(x)
#define GGML_F16x8_LOAD(x) vld1q_f16((const __fp16 *)(x))
#define GGML_F16x8_LOAD(x) vld1q_f16((const ggml_fp16_internal_t *)(x))
#define GGML_F16x8_STORE vst1q_f16
#define GGML_F16x8_FMA(a, b, c) vfmaq_f16(a, b, c)
#define GGML_F16x8_ADD vaddq_f16
@ -900,7 +900,7 @@ inline static float vaddvq_f32(float32x4_t v) {
#define GGML_F32Cx4 float32x4_t
#define GGML_F32Cx4_ZERO vdupq_n_f32(0.0f)
#define GGML_F32Cx4_SET1(x) vdupq_n_f32(x)
#define GGML_F32Cx4_LOAD(x) vcvt_f32_f16(vld1_f16((const __fp16 *)(x)))
#define GGML_F32Cx4_LOAD(x) vcvt_f32_f16(vld1_f16((const ggml_fp16_internal_t *)(x)))
#define GGML_F32Cx4_STORE(x, y) vst1_f16(x, vcvt_f16_f32(y))
#define GGML_F32Cx4_FMA(a, b, c) vfmaq_f32(a, b, c)
#define GGML_F32Cx4_ADD vaddq_f32