Skip to content

【GLM】fix glm sp bug #2746

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

Merged
merged 1 commit into from
Oct 17, 2025
Merged

【GLM】fix glm sp bug #2746

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
8 changes: 4 additions & 4 deletions paddleformers/transformers/glm4_moe/modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -440,17 +440,17 @@ def moe(self, hidden_states: paddle.Tensor, topk_indices: paddle.Tensor, topk_we
return final_hidden_states.cast(hidden_states.dtype)

def forward(self, hidden_states):
residuals = hidden_states
orig_shape = hidden_states.shape
if self.sequence_parallel:
hidden_states = GatherOp.apply(hidden_states)
residuals = hidden_states
orig_shape = hidden_states.shape
topk_indices, topk_weights = self.gate(hidden_states)
hidden_states = hidden_states.reshape((-1, hidden_states.shape[-1]))
hidden_states = self.moe(hidden_states, topk_indices, topk_weights)
if self.sequence_parallel:
hidden_states = ScatterOp.apply(hidden_states)
hidden_states = paddle.reshape(hidden_states, orig_shape)
hidden_states = hidden_states + self.shared_experts(residuals)
if self.sequence_parallel:
hidden_states = ScatterOp.apply(hidden_states)
return hidden_states


Expand Down