Skip to content

Increased searchLength and updated APPLY_PRIOR_TO_LAYERS #7

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

Open
styagi130 wants to merge 1 commit into
base: vklimkov/cfg
Choose a base branch
from
Open

Increased searchLength and updated APPLY_PRIOR_TO_LAYERS #7

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 cpp/tensorrt_llm/batch_manager/runtimeBuffers.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1029,7 +1029,7 @@ void RuntimeBuffers::setAttentionPriorIdx(
}

// create a cpu buffer for scores to find max score in
SizeType32 searchLength = 5;
SizeType32 searchLength = 15;
auto const& manager = runtime.getBufferManager();
auto const& stream = runtime.getStream();
auto scoresHost = manager.cpu(ITensor::makeShape({searchLength}), scores->getDataType());
Expand Down
2 changes: 1 addition & 1 deletion tensorrt_llm/models/t5tts/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@
}

COMPUTE_SCORES_FROM_LAYERS = [4,6,10]
APPLY_PRIOR_TO_LAYERS = [4,5,6,7,8,9,10,11]
APPLY_PRIOR_TO_LAYERS = [4,6,10]


class PositionwiseConvFF(Module):
Expand Down