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

ggml : fix arm build (#10890)

Browse source 
* ggml: GGML_NATIVE uses -mcpu=native on ARM

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* ggml: Show detected features with GGML_NATIVE

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* remove msvc support, add GGML_CPU_ARM_ARCH option

* disable llamafile in android example

* march -> mcpu, skip adding feature macros

ggml-ci

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
Co-authored-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Diego Devesa 2024-12-18 23:21:42 +01:00 • committed by GitHub
parent 0bf2d10c55
commit 9177484f58
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 69 additions and 95 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml/src/ggml-cpu/llamafile/sgemm.cpp
View file

@ -204,6 +204,7 @@ template <> inline float32x4_t load(const float *p) {
return vld1q_f32(p);
}
#if !defined(_MSC_VER)
// FIXME: this should check for __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
template <> inline float16x8_t load(const ggml_fp16_t *p) {
return vld1q_f16((const float16_t *)p);
}