PySpect

Home

Invoices

search

top

Package search

optimum-deepsparse

  • Summary: Optimum DeepSparse is an extension of the Hugging Face Transformers library that integrates the DeepSparse inference runtime. DeepSparse offers GPU-class performance on CPUs, making it possible to run Transformers and other deep learning models on commodity hardware with sparsity. Optimum DeepSparse provides a framework for developers to easily integrate DeepSparse into their applications, regardless of the hardware platform.
  • Author: Neuralmagic, Inc.
  • Homepage: https://github.com/neuralmagic/deepsparse
  • Source: https://github.com/neuralmagic/deepsparse
  • Repo profile
  • Number of releases: 2
  • First release: 0.1.0.dev0 on 2023-10-18T20:48:19
  • Latest release: 0.1.0.dev1 on 2023-10-26T02:02:44
Dependencies of optimum-deepsparse (11).
DependencyOptional
deepsparse-nightlyfalse
diffusersfalse
optimumfalse
blacktrue
evaluatetrue
parameterizedtrue
Pillowtrue
py-cpuinfotrue
pytesttrue
rufftrue
torchaudiotrue