Default Branch

18fdcc94e5 · docs: fix broken .md links and render issues (#13550) · Updated 2025-12-23 12:44:55 -05:00

Branches

2053ae5199 · app: allow more agentic models to use web search · Updated 2025-12-23 20:28:31 -05:00

0
1

6d9a37ad62 · cmd: add prompt rendering mcp · Updated 2025-12-23 16:41:25 -05:00

0
1

533541d97d · macOS · Updated 2025-12-22 20:12:52 -05:00

2
1

bf63d18b11 · linter · Updated 2025-12-21 01:46:46 -05:00

2
4

ebbebdf3b1 · better logging / fix defaults · Updated 2025-12-21 00:05:34 -05:00

2
11

76eebecd88 · WIP: preserve tool definition and call JSON ordering · Updated 2025-12-19 17:49:03 -05:00

3
1

6a4685edf5 · address comments · Updated 2025-12-19 15:27:15 -05:00

14
12

f82d00af74 · openai: do not separate images into their own messages · Updated 2025-12-18 17:07:31 -05:00

3
1

f03b8bc51a · ggml: Use max graph memory allocation when reserving · Updated 2025-12-18 14:14:17 -05:00

4
1

a6df9d75cf · also need to set type to omitempty to work · Updated 2025-12-17 21:55:28 -05:00

6
1

5584bf1e19 · cleanup + add tokenizer hash · Updated 2025-12-17 18:34:31 -05:00

7
4

4a0f90ec38 · Apply suggestion from @ParthSareen · Updated 2025-12-17 18:29:55 -05:00

8
2

f52671ecc6 · refactor: bpe and spm tokenizer merges · Updated 2025-12-17 16:36:32 -05:00

8
2

1200e427f7 · ollamarunner: Automatically enable flash attention · Updated 2025-12-17 16:09:49 -05:00

8
1

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

22
4

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

14
4

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

21
5

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

29
3

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

40
1

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

49
13