8 Commits

Author SHA1 Message Date
Louis
0b88d93e18
fix: top_k validation 2025-07-01 16:40:22 +07:00
Louis
db74f2cf3f
fix: check newValue not null 2025-07-01 13:28:30 +07:00
Louis
7b22ba8c54
fix: some of the model settings are not applied 2025-07-01 13:17:32 +07:00
Louis
1e8c9956cd
Merge pull request #5568 from menloresearch/fix/min_p-validation-on-model-load
fix: min p validation on model load
2025-07-01 11:15:35 +07:00
Louis
d407ebc4e9
fix: typo 2025-06-25 19:42:22 +07:00
Louis
a7c441ee58
🐛fix: default model settings for jan-nano-128k 2025-06-25 19:36:34 +07:00
Louis
2899d58ad7
🐛fix: llama.cpp default NGL setting does not offload all layers to GPU (#5310)
* 🐛fix: llama.cpp default NGL setting does not offload all layers to GPU

* chore: cover more cases

* chore: clean up

* fix: should not show GPU section on Mac
2025-06-17 15:30:07 +07:00
Louis
3643c8866e
fix: correct model settings on startup and strip down irrelevant model parameters 2024-11-04 15:37:18 +07:00