Default Branch

f6a016f49d · revert granite-embedding (#13505) · Updated 2025-12-16 18:44:52 -05:00

Branches

52a8b70100 · only add think to the most recent user message · Updated 2025-12-16 17:20:55 -05:00

3
4

fc1f10cd0b · fix test · Updated 2025-12-16 13:28:15 -05:00

12
4

89637ae43b · gemma2: enable flash attention · Updated 2025-12-16 12:45:05 -05:00

4
4

e1878e6e33 · remove cherry pick manually · Updated 2025-12-15 18:00:28 -05:00

11
5

a2cc0d9e47 · ollamarunner: Automatically enable flash attention · Updated 2025-12-12 18:26:22 -05:00

16
1

42d6a3f075 · proper clear draft message · Updated 2025-12-12 16:56:44 -05:00

19
3

3c0b0eaf04 · cleanup + add tokenizer hash · Updated 2025-12-11 18:44:41 -05:00

26
4

5d3eeb43c0 · convert: check file size for safetensors to warn for improper conversion · Updated 2025-12-10 20:58:16 -05:00

30
1

29a2d6d931 · fixed converter · Updated 2025-12-10 19:11:52 -05:00

39
13

071ac2116a · fix: ollama launchAgent plist · Updated 2025-12-10 17:34:30 -05:00

32
1

03abdb4969 · fixed pretokenizer · Updated 2025-12-09 13:02:17 -05:00

71
7

5c3bf414ef · close to working · Updated 2025-12-08 21:17:56 -05:00

71
10

3dcc31dfac · chore: remove embedded metal file · Updated 2025-12-08 16:25:14 -05:00

43
2

adadaa8eb9 · fix test · Updated 2025-12-08 15:57:35 -05:00

47
6

92af238208 · wip · Updated 2025-12-02 15:17:36 -05:00

65
2

32c6d43e1b · linter · Updated 2025-12-01 20:37:51 -05:00

70
4

7b152860c2 · linter: remove prealloc · Updated 2025-12-01 18:36:16 -05:00

67
1

d96fb7deb3 · cmd: add eval command for lightweight model evals · Updated 2025-11-28 19:38:13 -05:00

70
3

cee4922649 · added batch fix · Updated 2025-11-21 19:29:56 -05:00

71
1

0744f3edca · ggml: Use max graph memory allocation when reserving · Updated 2025-11-21 16:42:07 -05:00

71
1