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

metal : try to utilize more of the shared memory using smaller views

Browse source
This commit is contained in:
Georgi Gerganov 2023-06-26 22:23:04 +03:00
parent c824d2e368
commit 5cc672a9a5
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-metal.h
View file

@ -23,7 +23,7 @@
#include <stdbool.h>
// max memory buffers that can be mapped to the device
#define GGML_METAL_MAX_BUFFERS 16
#define GGML_METAL_MAX_BUFFERS 256
struct ggml_tensor;
struct ggml_cgraph;