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

Hotfixing qwen2 and starcoder2 (which also get clamping). #2167

Merged
merged 1 commit into from
Jul 2, 2024
Merged

Hotfixing qwen2 and starcoder2 (which also get clamping). #2167

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: 1 addition & 1 deletion server/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -368,7 +368,7 @@ def forward(
elif self.max_past is not None:
# Clamp in decode mode as paged attention requires clamped values whereas the flash attention
# kernel requires the true values
input_lengths = torch.clamp(input_lengths, max=self.max_past_tensor)
input_lengths = input_lengths.clamp(max=self.max_past_tensor)

hidden_states = self.model(
input_ids,
Expand Down
2 changes: 1 addition & 1 deletion server/text_generation_server/models/custom_modeling/flash_starcoder2_modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -534,7 +534,7 @@ def forward(
elif self.max_past is not None:
# Clamp in decode mode as paged attention requires clamped values whereas the flash attention
# kernel requires the true values
input_lengths = torch.clamp(input_lengths, max=self.max_past_tensor)
input_lengths = input_lengths.clamp(max=self.max_past_tensor)

hidden_states = self.model(
input_ids,
Expand Down
Loading