chenyu 93e3f952aa use BEAM=2 instead of BEAM=4 in cuda ci gpt2 (#3089) ... BEAM=2 is faster and less search time. investigating why BEAM2+BEAM4 is slower than BEAM2 alone		2024-01-11 13:21:06 -05:00
..
workflows	use BEAM=2 instead of BEAM=4 in cuda ci gpt2 (#3089)	2024-01-11 13:21:06 -05:00