Skip to content

[Example] Add 2:4 sparsity -> INT8 SmoothQuant PTQ -> ONNX -> TensorRT pipeline#1664

Draft
ajrasane wants to merge 5 commits into
mainfrom
ajrasane/sparse-quant-trt-example
Draft

[Example] Add 2:4 sparsity -> INT8 SmoothQuant PTQ -> ONNX -> TensorRT pipeline#1664
ajrasane wants to merge 5 commits into
mainfrom
ajrasane/sparse-quant-trt-example

Always quantize attention math; drop the --quant-attention flag

dff1aa1
Select commit
Loading
Failed to load commit list.