PaddleNLP
PaddleNLP copied to clipboard
[Unified Checkpoint] Accelerate loading checkpoint by multi-thread
trafficstars
PR types
Performance optimization
PR changes
Others
Description
Accelerate loading checkpoint (only safetensors) by multi-thread
Thanks for your contribution!
Codecov Report
Attention: Patch coverage is 42.50000% with 23 lines in your changes missing coverage. Please review.
Project coverage is 52.81%. Comparing base (
6211e3d) to head (2294105). Report is 259 commits behind head on develop.
| Files with missing lines | Patch % | Lines |
|---|---|---|
| paddlenlp/transformers/model_utils.py | 42.50% | 23 Missing :warning: |
Additional details and impacted files
@@ Coverage Diff @@
## develop #9034 +/- ##
===========================================
- Coverage 53.44% 52.81% -0.64%
===========================================
Files 664 660 -4
Lines 109935 106869 -3066
===========================================
- Hits 58757 56443 -2314
+ Misses 51178 50426 -752
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.