Shadowgraph
About
Sign in
← Papers

PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation

ACM:3600006.3613139 · 1 repo reference this paper in their README

microsoft/MInference

1,227

·

+0

·

Python

[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and…