- 03 Apr, 2020 1 commit
-
-
Neel Kant authored
-
- 01 Apr, 2020 1 commit
-
-
Neel Kant authored
-
- 31 Mar, 2020 3 commits
- 30 Mar, 2020 2 commits
- 27 Mar, 2020 1 commit
-
-
Neel Kant authored
-
- 26 Mar, 2020 5 commits
- 24 Mar, 2020 4 commits
- 11 Mar, 2020 2 commits
-
-
Raul Puri authored
memory optimization in mpu cross entropy See merge request ADLR/megatron-lm!32
-
Mohammad Shoeybi authored
-
- 10 Feb, 2020 2 commits
-
-
Jared Casper authored
Model parallel merger See merge request ADLR/megatron-lm!28
-
Mohammad Shoeybi authored
-
- 04 Feb, 2020 3 commits
-
-
Mohammad Shoeybi authored
fixed a bug on fp16 while generating samples See merge request ADLR/megatron-lm!29
-
Mostofa Patwary authored
-
Jared Casper authored
Scale Q*K (query times key) by 1/layer-number and add exponential decay option See merge request ADLR/megatron-lm!27
-
- 17 Jan, 2020 2 commits
- 14 Jan, 2020 3 commits
-
-
Mohammad Shoeybi authored
-
Mohammad Shoeybi authored
-
Mohammad Shoeybi authored
-
- 06 Jan, 2020 1 commit
-
-
Jared Casper authored
New data loader See merge request ADLR/megatron-lm!16
-
- 27 Dec, 2019 1 commit
-
-
Mohammad Shoeybi authored
-
- 26 Dec, 2019 3 commits
-
-
Mohammad Shoeybi authored
-
Mohammad Shoeybi authored
-
Mohammad Shoeybi authored
-
- 25 Dec, 2019 1 commit
-
-
Mohammad Shoeybi authored
-
- 22 Dec, 2019 1 commit
-
-
Raul Puri authored
-
- 04 Dec, 2019 1 commit
-
-
Mohammad Shoeybi authored
-
- 02 Dec, 2019 1 commit
-
-
Mohammad Shoeybi authored
-
- 27 Nov, 2019 2 commits
-
-
Mostofa Patwary authored
Refactor gpt2 See merge request ADLR/megatron-lm!15
-
Mohammad Shoeybi authored
-