"x/model/sentencepiece.go" did not exist on "34d0c55ea57e24d04b57e792f91a91eaa18ad9ce"
- 08 Jul, 2024 1 commit
-
-
Nicolas Patry authored
* Softcap v2 (fwd only). * Some missing interface + remove overrides in tests.
-
- 01 Jul, 2024 3 commits
-
-
66RING authored
-
Nicolas Patry authored
When user send `out` as a parameter of the function `seqlenq_ngroups_swapped` with parameters that trigger, the CHECK_SHAPE is incorrect (since q shape is modified.)
-
Liang authored
Co-authored-by:zl <zl@deepseek.com>
-
- 27 Jun, 2024 1 commit
-
-
Grigory Sizov authored
* Support unpadded LSE layout. Co-authored-by:
Xinfeng Xie <xfxie.ceca@gmail.com> Co-authored-by:
Jianyu Huang <hjyahead@gmail.com> * Cleanup * Fix unpadded LSE on split-kv path * Fix formatting and comments * Fix inline vs forceinline --------- Co-authored-by:
Xinfeng Xie <xfxie.ceca@gmail.com> Co-authored-by:
Jianyu Huang <hjyahead@gmail.com>
-
- 26 May, 2024 1 commit
-
-
Tri Dao authored
-
- 08 Apr, 2024 2 commits
- 28 Mar, 2024 2 commits
-
-
Driss Guessous authored
-
ljss authored
-
- 15 Mar, 2024 2 commits
-
-
Driss Guessous authored
-
Grigory Sizov authored
* Enable paged attention in varlen forward * Format + fix padding
-
- 21 Feb, 2024 1 commit
-
-
Tri Dao authored
-
- 20 Feb, 2024 1 commit
-
-
Tri Dao authored
-
- 10 Feb, 2024 2 commits
-
-
Tri Dao authored
-
Brian Hirsh authored
-
- 08 Feb, 2024 1 commit
-
-
Grigory Sizov authored
-
- 30 Jan, 2024 1 commit
-
-
Jeremy Reizenstein authored
For faster and smaller builds in some simple cases, provide switches to allow disabling -backward -alibi -uneven k -dropout -local attention Co-authored-by:Jeremy Francis Reizenstein <bottler@users.noreply.github.com>
-
- 23 Jan, 2024 2 commits
-
-
Tri Dao authored
Co-authored-by:ljss <450993438@qq.com>
-
Tri Dao authored
-
- 22 Jan, 2024 1 commit
-
-
Tri Dao authored
-
- 21 Jan, 2024 7 commits
- 20 Jan, 2024 1 commit
-
-
Tri Dao authored
-
- 15 Jan, 2024 2 commits
- 14 Jan, 2024 5 commits
- 13 Jan, 2024 2 commits
- 12 Jan, 2024 1 commit
-
-
Tri Dao authored
-
- 24 Dec, 2023 1 commit
-
-
Tri Dao authored
-