Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[one-cmds] Add fuse_rmsnorm option to one command #14076

Merged
merged 1 commit into from
Sep 24, 2024
Merged

[one-cmds] Add fuse_rmsnorm option to one command #14076

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions compiler/one-cmds/how-to-use-one-commands.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,6 +187,8 @@ Current transformation options are
- fuse_mean_with_mean: This fuses two consecutive ReduceMean operations into one.
- fuse_transpose_with_mean: This fuses ReduceMean with a preceding Transpose under certain conditions.
- fuse_horizontal_fc_layers: This fuses horizontal FullyConnected layers under certain conditions.
- fuse_rmsnorm: This will convert rms normalization related operators to
one RmsNormalization operator that our onert provides for faster execution.
- make_batchnorm_gamma_positive: This makes negative gamma of batch normalization into a small positive value (1e-10).
Note that this pass can change the execution result of the model.
So, use it only when the impact is known to be acceptable.
Expand Down
1 change: 1 addition & 0 deletions compiler/one-cmds/onelib/constant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,6 +146,7 @@ class CONSTANT:
('fuse_instnorm', 'fuse ops to InstanceNorm operator'),
('fuse_prelu', 'fuse ops to PReLU operator'),
('fuse_gelu', 'fuse ops to GeLU operator'),
('fuse_rmsnorm', 'fuse ops to RmsNorm operator'),
('fuse_rsqrt', 'fuse ops to Rsqrt operator'),
('replace_cw_mul_add_with_depthwise_conv',
'replace channel-wise Mul/Add with DepthwiseConv2D'),
Expand Down