Commit Graph

13 Commits (cfcfa4e4d28dcce91eb029c8a70d01042161403f)

Author SHA1 Message Date
Disty0 2264d8087b Pre-load support for NNCF 2025-04-22 04:35:36 +03:00
Vladimir Mandic 0f595d4cc5 cleanup multiple model loaders
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-11 22:16:05 -04:00
Vladimir Mandic 92af0036c6 add hidream
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-10 16:28:15 -04:00
Disty0 9b579bfd96 Move quant functions to model_quant.py 2025-01-23 21:50:26 +03:00
Vladimir Mandic 76755c6b6e switch gguf loader
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-21 09:19:51 -05:00
Vladimir Mandic ab07788ab5 add sana
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-12-16 11:30:15 -05:00
Vladimir Mandic cdcca50fb4 add model analyzer
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-10-14 13:03:46 -04:00
Vladimir Mandic ea0dfebe2d better handle any quant lib requirements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2024-10-12 13:36:16 -04:00
Vladimir Mandic 6919ca310a lint updates 2024-09-21 15:44:53 -04:00
Vladimir Mandic bdbd24ee66 expermental t5 gguf support 2024-09-20 12:52:52 -04:00
Fundaris f2bf7e8b87 fix setting t5 model 2024-09-19 20:40:49 +02:00
Vladimir Mandic 51e97b3e43 clear embeds cache on te change 2024-09-18 21:21:30 -04:00
Vladimir Mandic 2acb883dda jumbo update, see changelog 2024-09-18 13:48:30 -04:00