search

michaelfeil / infinity

Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.
https://michaelfeil.eu/infinity/
MIT License
977 stars 72 forks source link

Fp8 support #153

Closed michaelfeil closed 3 months ago

codecov-commenter commented 3 months ago

Codecov Report

Attention: Patch coverage is 30.76923% with 9 lines in your changes are missing coverage. Please review.

Project coverage is 72.25%. Comparing base (5264659) to head (5920059). Report is 1 commits behind head on main.

Files Patch % Lines
...infinity_emb/transformer/quantization/interface.py 10.00% 9 Missing :warning:

:exclamation: Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #153 +/- ## ========================================== - Coverage 72.67% 72.25% -0.42% ========================================== Files 32 32 Lines 1749 1759 +10 ========================================== Hits 1271 1271 - Misses 478 488 +10 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.