Signed-off-by: Jared Van Bortel <jared@nomic.ai> Co-authored-by: niansa <anton-sa@web.de> Co-authored-by: Adam Treat <treat.adam@gmail.com> Co-authored-by: Aaron Miller <apage43@ninjawhale.com> Co-authored-by: ToKiNoBug <tokinobug@163.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: slaren <slarengh@gmail.com>
22 lines
508 B
Plaintext
22 lines
508 B
Plaintext
#version 450
|
|
|
|
#include "common.comp"
|
|
|
|
layout(local_size_x = 1) in;
|
|
|
|
layout(binding = 0) buffer restrict readonly tensorIn { float in_[]; };
|
|
layout(binding = 1) buffer restrict writeonly tensorOut { float out_[]; };
|
|
layout(push_constant) uniform PushConstants {
|
|
uint inOff;
|
|
uint outOff;
|
|
} pcs;
|
|
|
|
void main() {
|
|
const uint baseIndex = gl_WorkGroupID.x * 4;
|
|
|
|
for (uint x = 0; x < 4; x++) {
|
|
const uint i = baseIndex + x;
|
|
out_[i + pcs.outOff] = max(0.0, in_[i + pcs.inOff]);
|
|
}
|
|
}
|