diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-07-27 07:55:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-07-27 07:55:01 +0200 |
| commit | 154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch) | |
| tree | 81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /ggml/src/vulkan-shaders/div.comp | |
| parent | 0684c3e9c70d49323b4fc517128cbe222cab7f96 (diff) | |
Merge mainline llama.cpp (#3)
* 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>
Diffstat (limited to 'ggml/src/vulkan-shaders/div.comp')
| -rw-r--r-- | ggml/src/vulkan-shaders/div.comp | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/ggml/src/vulkan-shaders/div.comp b/ggml/src/vulkan-shaders/div.comp new file mode 100644 index 00000000..8ee4bfc7 --- /dev/null +++ b/ggml/src/vulkan-shaders/div.comp @@ -0,0 +1,12 @@ +#version 450 + +#include "types.comp" +#include "generic_binary_head.comp" + +void main() { + if (gl_GlobalInvocationID.x >= p.ne) { + return; + } + + data_d[p.d_offset + dst_idx(gl_GlobalInvocationID.x)] = D_TYPE(FLOAT_TYPE(data_a[src0_idx(gl_GlobalInvocationID.x)]) / FLOAT_TYPE(data_b[src1_idx(gl_GlobalInvocationID.x)])); +} |