neuralmagic / deepsparse

Sparsity-aware deep learning inference runtime for CPUs
https://neuralmagic.com/deepsparse/
Other
2.97k stars 171 forks source link

[Pipeline Refactor] Add in top level aliases #1466

Closed dsikka closed 8 months ago

dsikka commented 8 months ago

Summary

from deepsparse import TextGeneration, CodeGeneration, Chat
model_path = "hf:neuralmagic/TinyLlama-1.1B-Chat-v0.4-pruned50-quant-ds"
pipeline = TextGeneration(model_path=model_path)