Skip to content

[FIX] Fix error max_seq_len == -1 #797

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

Merged
merged 1 commit into from
Aug 23, 2023
Merged

[FIX] Fix error max_seq_len == -1 #797

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 mlc_llm/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,7 @@ def mod_transform_before_build(
) # pylint: disable=not-callable

if "num_attention_heads" in config and "hidden_size" in config:
if args.max_seq_len:
if args.max_seq_len != -1:
mod = fuse_split_rotary_embedding(mod, config["num_attention_heads"], config["hidden_size"], args.max_seq_len)
else:
mod = fuse_split_rotary_embedding(mod, config["num_attention_heads"], config["hidden_size"])
Expand Down
1 change: 0 additions & 1 deletion mlc_llm/transform/fuse_split_rotary_embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,6 @@ def split_rotary(

def fuse_split_rotary_embedding(mod, num_attention_heads, hidden_size, max_sequence_length=2048):
head_dim = hidden_size // num_attention_heads
print(f"fuse_split_rotary_embedding {max_sequence_length}")

mod["split_rotary"] = get_split_rotary(num_attention_heads, head_dim, max_sequence_length)

Expand Down