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

only s_warptile_mmq needs to be run with 32 threads or more

Browse source
This commit is contained in:
Eve 2024-12-15 15:47:24 -05:00
parent 6110a9b36e
commit 663716ce42
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file

@ -1442,7 +1442,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
l_warptile = { 128, 128, 128, 16, device->subgroup_size * 2, 64, 2, tm_l, tn_l, tk_l, device->subgroup_size };
m_warptile = { 128, 64, 64, 16, device->subgroup_size, 32, 2, tm_m, tn_m, tk_m, device->subgroup_size };
s_warptile = { subgroup_size_32, 32, 32, 16, 32, 32, 2, tm_s, tn_s, tk_s, device->subgroup_size };
s_warptile = { subgroup_size_16, 32, 32, 16, 32, 32, 2, tm_s, tn_s, tk_s, device->subgroup_size };
l_warptile_mmq = { 128, 128, 128, 32, device->subgroup_size * 2, 64, 2, tm_l, tn_l, tk_l, device->subgroup_size };
m_warptile_mmq = { 128, 64, 64, 32, device->subgroup_size, 32, 2, tm_m, tn_m, tk_m, device->subgroup_size };