|
|
8149ac8c8b
|
rerank endpoint plugin
|
2026-01-20 22:01:23 +01:00 |
|
SERVICE GPGPU
|
6c7f96145b
|
add rerank endpoint
|
2026-01-20 20:44:48 +00:00 |
|
SERVICE GPGPU
|
ccbe95ac1e
|
additional coding-specific modelfiles
|
2026-01-19 21:55:49 +00:00 |
|
|
|
687e39c5e4
|
remove mis-placed file
|
2026-01-19 14:27:16 +01:00 |
|
|
|
c3597170f4
|
improve section headers
|
2026-01-19 14:22:17 +01:00 |
|
|
|
e2465f1289
|
model grouping
|
2026-01-19 14:16:02 +01:00 |
|
|
|
ee8ce9e831
|
fix qwen3 prompt templates
|
2026-01-19 14:12:20 +01:00 |
|
|
|
70d2ac8d36
|
fix context optimizer to search dowwards when baseline uses offload
|
2026-01-19 12:23:10 +01:00 |
|
|
|
b03bd70b81
|
fix: silent failures for context optimizer
|
2026-01-19 12:19:03 +01:00 |
|
|
|
f559170960
|
fix qwen3 modelfiles to include quantization info
|
2026-01-19 09:47:55 +01:00 |
|
|
|
2baaacd570
|
fix modelfiles for qwen3
|
2026-01-19 09:45:15 +01:00 |
|
|
|
2cf3b30e0d
|
adj ctx sizes
|
2026-01-18 23:37:16 +01:00 |
|
|
|
fa2c918ac7
|
todo list
|
2026-01-18 22:28:43 +01:00 |
|
|
|
7c89b12c3b
|
update modelfiles
|
2026-01-18 22:25:27 +01:00 |
|
|
|
ff9539c9dd
|
fix modelfiles
|
2026-01-18 22:23:06 +01:00 |
|
|
|
197e3b9037
|
qwen modelfiles
|
2026-01-18 22:21:00 +01:00 |
|
|
|
c40874d7f0
|
initial commit
|
2026-01-18 22:01:50 +01:00 |
|
|
|
ab25613358
|
Initial commit
|
2026-01-18 14:09:56 +00:00 |
|
