DeepSpeed

9bf77782 - Fix a bug in the implementation of dequantization for inference (#3433)

Fix a bug in the implementation of dequantization for inference (#3433) * bugfix in launch_dequantize() Get rid of `hid_cnt` and simply set #blocks to output size / #groups * add a unit test for dequantization --------- Co-authored-by: Logan Adams <114770087+loadams@users.noreply.github.com> Co-authored-by: Reza Yazdani <44502768+RezaYazdaniAminabadi@users.noreply.github.com>