Skip to content

test: fully mask idle batching slots #109

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
Connor1996 merged 1 commit into from
Mar 23, 2026
Merged

test: fully mask idle batching slots #109

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
3 changes: 0 additions & 3 deletions src/tiny_llm_ref/kv_cache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,9 +78,6 @@ def get_seq_len(data):
)
for b in range(B):
if data[b] is None:
# for some reasons we need to do this, otherwise it will cause wrong output?
# maybe precision issues?
masks[b, :, :] = causal_mask(mask_length, seq_len, dtype=key.dtype)
continue
key, value, S, mask = data[b]
keys[b, :, seq_len - S : seq_len, :] = key
Expand Down
2 changes: 1 addition & 1 deletion tests_refsol/test_week_2_day_6.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,7 +236,7 @@ def test_task_2_batching_kv_cache():
expected_mask = mx.array(
[
[[[-mx.inf, 0.0, 0.0, -mx.inf], [-mx.inf, 0.0, 0.0, 0.0]]],
[[[0.0, 0.0, 0.0, -mx.inf], [0.0, 0.0, 0.0, 0.0]]],
[[[-mx.inf, -mx.inf, -mx.inf, -mx.inf], [-mx.inf, -mx.inf, -mx.inf, -mx.inf]]],
[[[0.0, 0.0, 0.0, -mx.inf], [0.0, 0.0, 0.0, 0.0]]],
],
dtype=mx.float32,
Expand Down
Loading