Skip to content

Basic Bamba Rewrite + Numerical Precision #133

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 2 commits into from
Sep 18, 2025
Merged

Basic Bamba Rewrite + Numerical Precision #133

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1325c91
[None][auto_deploy] Bamba
2ez4bz Sep 6, 2025
267807f
debugging export accuracy diff for bamba
lucaslie Sep 17, 2025
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
1 change: 1 addition & 0 deletions tensorrt_llm/_torch/auto_deploy/custom_ops/attention_interface.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,6 +304,7 @@ def named_dynamic_shapes(self) -> Dict[str, Dict[str, Dim]]:
if self.max_batch_size > 1:
bs_seq_len_shape[0] = Dim("batch_size", max=self.max_batch_size)
bs_seq_len_shape[1] = Dim("seq_len", max=self.max_seq_len)
# bs_seq_len_shape[1] = Dim.AUTO
Copy link

Copilot AI Sep 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Commented-out code should be removed rather than left in the codebase. If this alternative implementation is needed for future reference, consider adding a TODO comment explaining when it should be used.

Suggested change
# bs_seq_len_shape[1] = Dim.AUTO

Copilot uses AI. Check for mistakes.
self._dynamic_shapes = {k: bs_seq_len_shape for k in self._uncached_arg_names}
# cached args are static
self._dynamic_shapes.update({k: {} for k in self._cached_arg_names})
Expand Down
Loading
Loading