search

neuralmagic / deepsparse

Sparsity-aware deep learning inference runtime for CPUs
https://neuralmagic.com/deepsparse/
Other
3.01k stars 176 forks source link

Revert #1263 #1293

Closed SageMoore closed 1 year ago

SageMoore commented 1 year ago

We've resolved the segfault that was occurring in sparse quantized MPT prefill so we can reenable external input deallocation.