Skip to content

Negative KV sequence length error in Attention op #4316

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
jinminxi104 wants to merge 1 commit into
base: main
Choose a base branch
from
+1 −1
Open

Negative KV sequence length error in Attention op #4316

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 lmdeploy/pytorch/engine/inputs_maker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -466,7 +466,7 @@ def create_model_inputs_delta(self):
if self.scheduler.cache_config.window_size > 0:
num_ignored_history = torch.tensor([msg.num_ignored_history for msg in valid_seqs])
else:
num_ignored_history = None
num_ignored_history = torch.zeros(len(valid_seqs), dtype=torch.long)

kv_seqlens = [seq.num_all_ids + max_q_seqlen for seq in valid_seqs]
sum_kv_seqlen = sum(kv_seqlens) + batch_size * max_q_seqlen
Expand Down
Loading