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

Jump to bottom

optimize calculation of cu_seqlens from position_ids #1084

Merged
merged 1 commit into from
Jan 10, 2024
Merged

optimize calculation of cu_seqlens from position_ids #1084

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
3 changes: 2 additions & 1 deletion src/axolotl/monkeypatch/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@ def get_cu_seqlens(attn_mask):
return torch.stack(results).to(dtype=torch.int32), torch.stack(max_seq_lens)


@torch.jit.script
def get_cu_seqlens_from_pos_ids(position_ids):
"""generate a cumulative sequence length mask for flash attention using pos ids"""
if len(position_ids.shape) == 1:
Expand All @@ -81,7 +82,7 @@ def get_cu_seqlens_from_pos_ids(position_ids):
# Get the indices where the sequence starts
start_indices = torch.cat(
[
(seq_starts).nonzero(as_tuple=True)[0],
torch.nonzero(seq_starts).unbind(dim=1)[0],
torch.tensor([len(adjusted_row)], dtype=torch.int32, device=device),
]
)
Expand Down