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

ggml, ci : Windows ARM runner and build fixes (#5979)

Browse source 
* windows arm ci

* fix `error C2078: too many initializers` with ggml_vld1q_u32 macro for MSVC ARM64

* fix `warning C4146: unary minus operator applied to unsigned type, result still unsigned`

* fix `error C2065: '__fp16': undeclared identifier`
This commit is contained in:
Michael Podvitskiy 2024-03-11 10:28:51 +01:00 • committed by GitHub
parent 332bdfd798
commit 3202361c5b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 21 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

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