- 15 Aug, 2023 1 commit
-
-
Ji Lin authored
Add compatibility with GQA & optimize multi-GPU memory allocation
-
- 14 Aug, 2023 2 commits
-
-
Jiaming Tang authored
-
Jiaming Tang authored
-
- 05 Aug, 2023 1 commit
-
-
Ji Lin authored
TinyChat: Fix logic for selecting MPT prompt templates (support for 8k variant).
-
- 02 Aug, 2023 2 commits
- 01 Aug, 2023 3 commits
-
-
Song authored
-
Haotian (Ken) Tang authored
-
Haotian Tang authored
-
- 27 Jul, 2023 1 commit
-
-
Casper authored
-
- 26 Jul, 2023 1 commit
-
-
Jiaming Tang authored
-
- 25 Jul, 2023 1 commit
-
-
Casper authored
Recently, MPT added an 8k context variant. I updated the logic so that the new chat models run as was originally intended.
-
- 24 Jul, 2023 13 commits
-
-
Ji Lin authored
Add TinyChat
-
Ji Lin authored
-
Haotian Tang authored
-
Haotian Tang authored
-
Haotian (Ken) Tang authored
-
ys-2020 authored
-
Shang Yang authored
-
Haotian (Ken) Tang authored
-
Haotian (Ken) Tang authored
-
Haotian (Ken) Tang authored
-
Haotian (Ken) Tang authored
-
Haotian Tang authored
-
Haotian Tang authored
-
- 21 Jul, 2023 1 commit
-
-
Ji Lin authored
-
- 20 Jul, 2023 3 commits
-
-
Jiaming Tang authored
-
Jiaming Tang authored
-
Jiaming Tang authored
-
- 19 Jul, 2023 1 commit
-
-
Abhinav Kulkarni authored
-
- 10 Jul, 2023 1 commit
-
-
Jiaming Tang authored
-
- 09 Jul, 2023 1 commit
-
-
Abhinav Kulkarni authored
-
- 06 Jul, 2023 1 commit
-
-
Sakits authored
-
- 04 Jul, 2023 4 commits
-
-
Jiaming Tang authored
-
Jiaming Tang authored
-
Abhinav Kulkarni authored
-
Abhinav Kulkarni authored
-
- 03 Jul, 2023 1 commit
-
-
Abhinav Kulkarni authored
-
- 01 Jul, 2023 2 commits
-
-
Abhinav Kulkarni authored
[Major] Add CPU offloading support for apply_scale, apply_clip, pseudo_quantize_model_weight, real_quantize_model_weight
-
Abhinav Kulkarni authored
[Major] Add CPU offloading support for apply_scale, apply_clip, pseudo_quantize_model_weight, real_quantize_model_weight
-
