Skip to content

Cast outputs to input dtypes; add result CSVs #11

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
Vishal-sys-code merged 1 commit into from
Apr 12, 2026
Merged

Cast outputs to input dtypes; add result CSVs #11

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
1 change: 1 addition & 0 deletions results/retrieval_VLACombined_256.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
epoch,train_loss,train_acc,test_acc,epoch_time_sec
Empty file added results/retrieval_VLAKVExploding_256.csv
View file
Open in desktop
Empty file.
6 changes: 3 additions & 3 deletions src/models/attention/fast_vla.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,15 +6,15 @@

# Try importing Triton
try:
import triton
import triton.language as tl
import triton # type: ignore
import triton.language as tl # type: ignore
HAS_TRITON = True
except ImportError:
HAS_TRITON = False

def _combine(F_l, G_l, F_r, G_r):
"""Associative operator for the (F, G) recurrence."""
return torch.matmul(F_r, F_l), torch.matmul(F_r, G_l) + G_r
return torch.matmul(F_r, F_l).to(F_l.dtype), (torch.matmul(F_r, G_l) + G_r).to(G_l.dtype)

def parallel_scan(Fs, Gs):
"""
Expand Down
Loading