- 06 Dec, 2021 5 commits
- 05 Dec, 2021 3 commits
- 03 Dec, 2021 3 commits
- 02 Dec, 2021 6 commits
- 28 Nov, 2021 1 commit
-
-
zihanl authored
-
- 27 Nov, 2021 3 commits
- 26 Nov, 2021 3 commits
- 24 Nov, 2021 4 commits
-
-
zihanl authored
-
Jared Casper authored
Fixed distributed checkpoint activations to work on all layers See merge request ADLR/megatron-lm!365
-
Jared Casper authored
Add support for signal-based dynamic checkpointing See merge request ADLR/megatron-lm!361
-
Szymon Migacz authored
-
- 23 Nov, 2021 1 commit
-
-
Lawrence McAfee authored
-
- 22 Nov, 2021 5 commits
-
-
Lawrence McAfee authored
-
Lawrence McAfee authored
-
Lawrence McAfee authored
-
zihanl authored
-
zihanl authored
-
- 21 Nov, 2021 1 commit
-
-
zihanl authored
-
- 18 Nov, 2021 2 commits
-
-
Jared Casper authored
add a kernel import guard for persistent layer norm See merge request ADLR/megatron-lm!363
-
Sangkug Lym authored
-
- 17 Nov, 2021 1 commit
-
-
Jared Casper authored
Persistent layer norm See merge request ADLR/megatron-lm!351
-
- 11 Nov, 2021 1 commit
-
-
Sangkug Lym authored
fix the guard to fall back to the baseline fused layer norm kernel Persisten ln: move the guard for supported hidden sizes to layer norm module
-
- 05 Nov, 2021 1 commit
-
-
Jared Casper authored
Fix finetuning tasks after T5 pipeline merge. See merge request ADLR/megatron-lm!343
-