neuralmagic / deepsparse

Sparsity-aware deep learning inference runtime for CPUs
https://neuralmagic.com/deepsparse/
Other
2.99k stars 173 forks source link

[TextGeneration] Update defaults to always start with deepsparse defaults when using the `generation_config` arg #1528

Closed dsikka closed 8 months ago

dsikka commented 8 months ago

Summary

Also takes care of this discussion: https://app.asana.com/0/1205229323407165/1206280624568198/f