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

ggml : move AMX to the CPU backend (#10570)

Browse source 
* ggml : move AMX to the CPU backend

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Diego Devesa 2024-11-29 21:54:58 +01:00 • committed by GitHub
parent b782e5c7d4
commit 7cc2d2c889
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
64 changed files with 514 additions and 801 deletions
Download patch file Download diff file Expand all files Collapse all files

10
ggml/src/ggml-impl.h
View file

@ -30,11 +30,13 @@
extern "C" {
#endif
#undef MIN
#undef MAX
#ifndef MIN
# define MIN(a, b) ((a) < (b) ? (a) : (b))
#endif
#define MIN(a, b) ((a) < (b) ? (a) : (b))
#define MAX(a, b) ((a) > (b) ? (a) : (b))
#ifndef MAX
# define MAX(a, b) ((a) > (b) ? (a) : (b))
#endif
// required for mmap as gguf only guarantees 32-byte alignment
#define TENSOR_ALIGNMENT 32