Skip to content

remove buggy duplicated code #609

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
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

remove buggy duplicated code #609

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: 0 additions & 8 deletions src/fastertransformer/layers/attention_layers/GptContextAttentionLayer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -565,14 +565,6 @@ void GptContextAttentionLayer<T>::allocateBuffer(size_t batch_size, size_t seq_l
}
}

if (int8_mode_ == 1) {
// We use max_size for n and k since we reuse buffers for both FCs and want to allocate the max
// possible memory that would be required by any of the individual gemms.
const int max_size = std::max(hidden_units_, 3 * local_hidden_units_);
mixed_gemm_ws_bytes_ = weight_only_int8_fc_runner_->getWorkspaceSize(batch_size * seq_len, max_size, max_size);
mixed_gemm_workspace_ = (char*)allocator_->reMalloc(mixed_gemm_workspace_, mixed_gemm_ws_bytes_, false);
}

if (int8_mode_ == 1) {
// We use max_size for n and k since we reuse buffers for both FCs and want to allocate the max
// possible memory that would be required by any of the individual gemms.
Expand Down