Skip to content

[JAX] Replace jnp.clip(..., a_min=..., a_max=...) with jnp.clip(..., min=..., max=...). #3512

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

Closed
copybara-service wants to merge 1 commit into from
Closed

[JAX] Replace jnp.clip(..., a_min=..., a_max=...) with jnp.clip(..., min=..., max=...). #3512

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
10 changes: 8 additions & 2 deletions src/maxtext/layers/moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -598,8 +598,14 @@ def apply_ffn_activation(self, layer_w0, layer_w1):
"""Applies FFN activation function."""
with jax.named_scope("ffn_act"):
if self.config.decoder_block == ctypes.DecoderBlockType.GPT_OSS:
layer_w0 = jnp.clip(layer_w0, a_min=None, a_max=self.config.mlp_activations_limit)
layer_w1 = jnp.clip(layer_w1, a_min=-self.config.mlp_activations_limit, a_max=self.config.mlp_activations_limit)
layer_w0 = jnp.clip(
layer_w0, min=None, max=self.config.mlp_activations_limit
)
layer_w1 = jnp.clip(
layer_w1,
min=-self.config.mlp_activations_limit,
max=self.config.mlp_activations_limit,
)
layer_act = self.activation_fn(layer_w0 * 1.702)
glu = jnp.multiply(layer_w0, layer_act)
intermediate_layer = jnp.multiply(glu, (layer_w1 + 1))
Expand Down
10 changes: 8 additions & 2 deletions tests/utils/forward_pass_logit_checker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,8 +332,14 @@ def main(config, test_args): # pylint: disable=W0621
max_logging.log(msg)

if test_args.clip_logits_epsilon is not None:
model_probabilities = jnp.clip(jax.nn.softmax(train_logits_slice, axis=-1), a_min=test_args.clip_logits_epsilon)
golden_probabilities = jnp.clip(jax.nn.softmax(golden_logits_slice, axis=-1), a_min=test_args.clip_logits_epsilon)
model_probabilities = jnp.clip(
jax.nn.softmax(train_logits_slice, axis=-1),
min=test_args.clip_logits_epsilon,
)
golden_probabilities = jnp.clip(
jax.nn.softmax(golden_logits_slice, axis=-1),
min=test_args.clip_logits_epsilon,
)
else:
model_probabilities = jax.nn.softmax(train_logits_slice, axis=-1)
golden_probabilities = jax.nn.softmax(golden_logits_slice, axis=-1)
Expand Down
Loading