- 11 Oct, 2021 1 commit
-
-
mshoeybi authored
-
- 10 Oct, 2021 1 commit
-
-
mshoeybi authored
-
- 08 Oct, 2021 1 commit
-
-
mshoeybi authored
-
- 07 Oct, 2021 2 commits
- 06 Oct, 2021 1 commit
-
-
Sangkug Lym authored
-
- 05 Oct, 2021 1 commit
-
-
Masaki Kozuki authored
-
- 02 Oct, 2021 1 commit
-
-
rprenger authored
-
- 01 Oct, 2021 2 commits
-
-
Jared Casper authored
Adds some backward compatibility code so old inference code still works.
-
mshoeybi authored
-
- 30 Sep, 2021 2 commits
- 29 Sep, 2021 4 commits
-
-
Jared Casper authored
-
mshoeybi authored
-
mshoeybi authored
-
mshoeybi authored
-
- 27 Sep, 2021 1 commit
-
-
mshoeybi authored
-
- 24 Sep, 2021 1 commit
-
-
mshoeybi authored
-
- 23 Sep, 2021 5 commits
- 22 Sep, 2021 3 commits
- 21 Sep, 2021 2 commits
- 20 Sep, 2021 3 commits
-
-
Mohammad Shoeybi authored
-
rprenger authored
-
rprenger authored
-
- 17 Sep, 2021 1 commit
-
-
Robert Clark authored
A temperature value between 0.0 and 100.0 can now be specified via the API while running the text generation server. The value passed to --temperature while running the text generation server is kept as the default value for all API calls that don't include temperature, even if different values were manually specified previously. Signed-Off-By:Robert Clark <roclark@nvidia.com>
-
- 14 Sep, 2021 3 commits
- 13 Sep, 2021 1 commit
-
-
rprenger authored
Changing the interface to the lm eval harness and fixing bugs caused by misunderstanding out_seq_length
-
- 07 Sep, 2021 1 commit
-
-
Sangkug Lym authored
-
- 03 Sep, 2021 2 commits
- 02 Sep, 2021 1 commit
-
-
slym authored
-
