tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2023-11-13 16:55:52 +02:00
committed by GitHub
parent c049b37d7b
commit 3d68f364f1
8 changed files with 586 additions and 1075 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml-impl.h
View File

@ -39,12 +39,6 @@ extern "C" {
#endif
#endif
#undef MIN
#undef MAX
#define MIN(a, b) ((a) < (b) ? (a) : (b))
#define MAX(a, b) ((a) > (b) ? (a) : (b))
// 16-bit float
// on Arm, we use __fp16
// on x86, we use uint16_t