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

Update ggml-metal.m

Browse source 
Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
This commit is contained in:
Matteo Boschini 2023-07-31 07:52:46 +02:00 • committed by Matteo Boschini
parent ae58ac7dd4
commit fee39ecd48
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-metal.m
View file

@ -749,7 +749,7 @@ void ggml_metal_graph_compute(
initWithDevice:ctx->device transposeLeft:false transposeRight:true
resultRows:ne11 resultColumns:ne01 interiorColumns:ne00 alpha:1.0 beta:0.0];
// we need to do ne02 multiplications
// we need to do ne12 multiplications
// TODO: is there a way to do this in parallel - currently very slow ..
// TODO: might be possible to offload part of the computation to ANE using Accelerate's CBLAS
for (int64_t i02 = 0; i02 < ne12; ++i02) {