Default Branch

2d039ecb65 · Merge pull request #149 from docker/sandboxing · Updated 2025-09-02 22:26:04 +08:00

Branches

e259edb647 · inference: Return memory requirement in estimation error · Updated 2025-08-29 21:35:53 +08:00

9
1

d370bbddbc · Move passthrough model name to constant and clarify error message. · Updated 2025-07-11 20:06:09 +08:00

86
6

66ce06c63b · Bump model-distribution to include total on pull/push progress messages · Updated 2025-07-03 23:30:47 +08:00

86
1

5a6fd96347 · wrap ResponseRecorder to avoid a race during tests · Updated 2025-06-13 23:29:59 +08:00

116
2

2fc84cfa33 · Include llama-server output in server error · Updated 2025-05-30 19:37:30 +08:00

142
1

9b10f3b345 · llamacpp: Skip model warmup · Updated 2025-05-22 14:57:16 +08:00

160
1

52beb06048 · llamacpp: Enable flash attention · Updated 2025-05-21 17:35:47 +08:00

166
1

354962c9af · Removes unneeded logs · Updated 2025-04-29 17:57:40 +08:00

204
15

a47583dc39 · Basic param tuning on windows/arm64 · Updated 2025-04-25 19:39:23 +08:00

206
2

87fd6f6466 · Fix llama-server auto update · Updated 2025-04-24 23:31:42 +08:00

208
0
Included

1de99bc202 · Added delete example · Updated 2025-04-24 16:30:28 +08:00

209
3

858b905c5d · Allow force deletion of multiply tagged models · Updated 2025-04-19 06:28:49 +08:00    docker

210
0
Included

247f63df65 · Handle missing models dir · Updated 2025-04-19 06:02:32 +08:00    docker

212
0
Included

6a781b0eeb · Set openAI id to model ID when untagged · Updated 2025-04-19 01:02:16 +08:00    docker

214
0
Included

eab9cf8f2b · make tag required · Updated 2025-04-18 09:57:25 +08:00    docker

216
0
Included

739247ee02 · Revert "Add endpoint for tagging a model" · Updated 2025-04-18 04:42:02 +08:00    docker

224
0
Included

e607ddcc49 · Update pkg/inference/models/manager.go · Updated 2025-04-18 02:44:08 +08:00    docker

238
0
Included

991d931ada · On ErrModelNotFound returns 404 · Updated 2025-04-15 17:54:16 +08:00    docker

241
2

7619921d11 · gofumpt -l -extra -w . · Updated 2025-04-10 23:31:23 +08:00    docker

244
4

9c16427ada · main.go: Add llama.cpp and scheduler for full experience · Updated 2025-04-10 16:36:19 +08:00    docker

246
0
Included