Skip to content
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

Fix rotating kv cache size #1093

Merged
merged 1 commit into from
Nov 5, 2024
Merged

Fix rotating kv cache size #1093

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 llms/mlx_lm/models/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ def create_attention_mask(h: mx.array, cache: Optional[Any] = None):
if cache is not None and cache[0] is not None:
c = cache[0]
if hasattr(c, "max_size"):
offset = min(c.max_size - 1, c.offset)
offset = min(c.max_size, c.offset)
window_size = c.max_size
else:
offset = c.offset
Expand Down
4 changes: 2 additions & 2 deletions llms/mlx_lm/models/cache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -325,9 +325,9 @@ def _update_concat(self, keys, values):
self.keys = self._temporal_order(self.keys)
self.values = self._temporal_order(self.values)

# The largest size is self.max_size + S - 1 to ensure
# The largest size is self.max_size + S to ensure
# every token gets at least self.max_size context
trim_size = self._idx - self.max_size + 1
trim_size = self._idx - self.max_size
self.keys = self._trim(trim_size, self.keys, keys)
self.values = self._trim(trim_size, self.values, values)
self.offset += keys.shape[2]
Expand Down