- 26 Oct, 2023 1 commit
-
-
Dan Yao authored
Grouped Query Attention/Multi Query Attention
-
- 18 Oct, 2023 4 commits
- 17 Oct, 2023 2 commits
-
-
Qianfeng Zhang authored
-
Qianfeng Zhang authored
reinterpret_cast to const char* in dumpBufferToFile to be compatible with both const and non-const input pointers
-
- 13 Oct, 2023 3 commits
-
-
ltqin authored
Two tiny updates
-
Qianfeng Zhang authored
-
Qianfeng Zhang authored
-
- 11 Oct, 2023 4 commits
- 10 Oct, 2023 7 commits
-
-
letaoqin authored
-
Dan Yao authored
Some tiny updates
-
Qianfeng Zhang authored
-
Qianfeng Zhang authored
-
Qianfeng Zhang authored
-
Dan Yao authored
flash attention remove fwd deterministic
-
letaoqin authored
-
- 09 Oct, 2023 2 commits
-
-
Qianfeng Zhang authored
-
danyao12 authored
-
- 08 Oct, 2023 2 commits
-
-
Qianfeng Zhang authored
-
Qianfeng Zhang authored
-
- 27 Sep, 2023 4 commits
- 26 Sep, 2023 11 commits