michaelfeil / infinity

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip
https://michaelfeil.github.io/infinity/
MIT License
1.32k stars 97 forks source link

add engine args similar to vllm #102

Closed michaelfeil closed 7 months ago

codecov-commenter commented 7 months ago

Codecov Report

Attention: 3 lines in your changes are missing coverage. Please review.

Comparison is base (8974edf) 86.28% compared to head (a3edded) 85.62%.

Files Patch % Lines
libs/infinity_emb/infinity_emb/engine.py 92.30% 1 Missing :warning:
...b/infinity_emb/transformer/crossencoder/optimum.py 0.00% 1 Missing :warning:
...y_emb/infinity_emb/transformer/embedder/optimum.py 0.00% 1 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 #102 +/- ## ========================================== - Coverage 86.28% 85.62% -0.66% ========================================== Files 27 28 +1 Lines 1276 1301 +25 ========================================== + Hits 1101 1114 +13 - Misses 175 187 +12 ```

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