Uh oh!
There was an error while loading. Please reload this page.
[JAX] Unifying GeLU and GeGLU in LayerNorm MLP - #765
Conversation
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
test_layer.py, and test_praxis_layer.py Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
zlsh80826
commented
Apr 10, 2024
/te-ci jax |
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
denera
commented
Apr 15, 2024
denera
commented
Apr 15, 2024
@phu0ngng Also please fix the linting errors here before the CI. Thanks! |
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
phu0ngng
commented
Apr 19, 2024
/te-ci jax |
Uh oh!
There was an error while loading. Please reload this page.
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
phu0ngng
commented
Apr 22, 2024
/te-ci jax |
phu0ngng
commented
Apr 22, 2024
Hi @denera, @mingxu1067, |
zlsh80826
commented
Apr 26, 2024
Congratulations on your first pull request! @phu0ngng |
* combined layernorm_geglu with layernorm_gelu into fused_layernorm Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> * fixes to pass all unit tests in test_custom_call_compute.py, test_layer.py, and test_praxis_layer.py Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> * cleaning and formatting Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> * renaming based on reviewers suggestions Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> * implemented partial fused layernorm Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> * geglu + bias passed tests Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> * added partial fused calculation for dbias_1 Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> * clean up Co-authored-by: Alp Dener <adener@nvidia.com> Signed-off-by: Phuong Nguyen <36155692+phu0ngng@users.noreply.github.com> --------- Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com> Signed-off-by: Phuong Nguyen <36155692+phu0ngng@users.noreply.github.com> Co-authored-by: Alp Dener <adener@nvidia.com> Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>
This PR unifies the GeLU and GEGLU implementations in
LayerNormMLPvia a generalizedfused_layernorm_fp8_mlp. Previously, there were two separate APIs for the two mentioned activations. The new routine takesactivation_type: Tupleanduse_bias: boolas two additional arguments, compared to old routines.This is a preparation step for adding more activations (i.e.
swiglu) later.