projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 1df526c) | patch
[GPU/OPENCL] RMSNorm Accuracy Fix
authorThummala Pallavi <t.pallavi@samsung.com>
Fri, 2 Aug 2024 06:41:34 +0000 (12:11 +0530)
committerJijoong Moon <jijoong.moon@samsung.com>
Mon, 19 Aug 2024 07:28:18 +0000 (16:28 +0900)
commit905a5b11decafa725928a0fcdd3a4e952a94ee0a
tree9a18a628e4eb752ef9b023ef9d0038838b9cc911tree | snapshot
parent1df526c15a36f75ea7d5b7a47589aaaadd89f728commit | diff
[GPU/OPENCL] RMSNorm Accuracy Fix

The alpha values were not picked correctly.

Signed-off-by: Thummala Pallavi <t.pallavi@samsung.com>
nntrainer/layers/cl_layers/rmsnorm_layer_cl.cpp diff | blob | history
Domain: Machine Learning / ML Framework;