CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)

Browse Source 
* ggml : move FP16 <-> FP32 stuff to ggml-impl.h

ggml-ci

* tests : fix ARM build

* ggml : explicitly initialize deprecated type traits

* ggml : add math.h to ggml-impl.h

* ggml : remove duplicate static assert macros

* ggml : prefix lookup tables with ggml_

ggml-ci

* ggml-impl : move extern "C" to start of file
This commit is contained in:
Georgi Gerganov
2023-10-30 19:19:15 +02:00
committed by GitHub
parent 6e08281e58
commit 207b51900e
7 changed files with 470 additions and 424 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/test-double-float.cpp
View File

@@ -4,7 +4,7 @@
#undef NDEBUG
#include <cassert>
#if !defined(__riscv) && !defined(__s390__)
#if !defined(__riscv) && !defined(__s390__) && !defined(__ARM_NEON)
#include <immintrin.h>
#endif
#include <cmath>

7
tests/test-quantize-fns.cpp
View File

@@ -129,6 +129,13 @@ int main(int argc, char * argv[]) {
ggml_type type = (ggml_type) i;
ggml_type_traits_t qfns = ggml_internal_get_type_traits(type);
// deprecated - skip
if (qfns.blck_size == 0) {
continue;
}
printf("Testing %s\n", ggml_type_name((ggml_type) i));
if (qfns.from_float && qfns.to_float) {
const float total_error = total_quantization_error(qfns, test_size, test_data.data());
const float max_quantization_error =