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

Added support for GGML_OP_CLAMP in Metal (#6662)

Browse source 
* Added support for GGML_OP_CLAMP in Metal

* Corrected size

---------

Co-authored-by: dave-fl <dave@Davids-MacBook-Pro.local>
This commit is contained in:
Dave 2024-04-14 07:14:19 -04:00 • committed by GitHub
parent 8800226d65
commit 422c2aff1c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 31 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

9
ggml-metal.metal
View file

@ -213,6 +213,15 @@ kernel void kernel_scale_4(
dst[tpig] = src0[tpig] * scale;
}
kernel void kernel_clamp(
device const float * src0,
device float * dst,
constant float & min,
constant float & max,
uint tpig[[thread_position_in_grid]]) {
dst[tpig] = src0[tpig] < min ? min : (src0[tpig] > max ? max : src0[tpig]);
}
kernel void kernel_relu(
device const float * src0,
device float * dst,