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

metal : localized logic in ggml_metal_graph_compute (#4924)

Browse Source 
* Metal: Localized logic in `ggml_metal_graph_compute`, minor performance improvement

* Whitespace

* Collecting command buffer completions on single thread

* Whitespace

* Reduce diff noise
This commit is contained in:
Paul Tsochantaris
2024-01-16 17:05:19 +00:00
committed by GitHub
parent 862f5e41ab
commit 158f8c9e21
2 changed files with 17 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml-metal.h
View File

@@ -27,7 +27,6 @@
// max memory buffers that can be mapped to the device
#define GGML_METAL_MAX_BUFFERS 64
#define GGML_METAL_MAX_COMMAND_BUFFERS 32
struct ggml_tensor;
struct ggml_cgraph;