Optimize model loading with encoder caching - #74
Open
adsharma wants to merge 10 commits into
Open
Conversation
adsharma
changed the title
- Default to local_files_only=True to avoid HF hub noise - Add encoder caching to speed up subsequent loads - First load: ~2.3s (encoder init is the bottleneck) - Subsequent loads: ~0.13s (20x faster with deep copy caching)
adsharma
force-pushed
the
imports_fixes
branch
from
February 24, 2026 06:42
d5c97f1 to
4c2fa2e
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Shaves about a second from this benchmark:
Still takes 3.7 secs vs 4.7 secs before. Anything we can do to defer more work?
Fixes: #60