ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 02:41:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge mainline llama.cpp (#3)

Browse Source 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-07-27 07:55:01 +02:00
committed by GitHub
parent 0684c3e9c7
commit 154e0d75fc
612 changed files with 50817 additions and 165936 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
ggml/src/vulkan-shaders/copy.comp Normal file
View File

@@ -0,0 +1,16 @@
#version 450
#include "types.comp"
#include "generic_unary_head.comp"
void main() {
if (gl_GlobalInvocationID.x >= p.ne) {
return;
}
#ifndef OPTIMIZATION_ERROR_WORKAROUND
data_d[p.d_offset + dst_idx(gl_GlobalInvocationID.x)] = D_TYPE(data_a[src0_idx(gl_GlobalInvocationID.x)]);
#else
data_d[p.d_offset + dst_idx(gl_GlobalInvocationID.x)] = data_a[src0_idx(gl_GlobalInvocationID.x)];
#endif
}