Commit Graph

11 Commits (ad34c2bdd40a8226f82b9637f17119d528cde838)

Author SHA1 Message Date
Jared Van Bortel 061d1969f8
expose n_gpu_layers parameter of llama.cpp (#1890)
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Jared Van Bortel d1c56b8b28
Implement configurable context length (#1749) 9 months ago
Jared Van Bortel d4ce9f4a7c
llmodel_c: improve quality of error messages (#1625) 11 months ago
Juuso Alasuutari 5cfb1bda89
llmodel: add model wrapper destructor, fix mem leak in golang bindings (#862)
Signed-off-by: Juuso Alasuutari <juuso.alasuutari@gmail.com>
1 year ago
Ettore Di Giacinto 44dc1ade62
Set thread counts after loading model (#836) 1 year ago
mudler 682a383e06 Drop leftover include 1 year ago
mudler 243c762411 Style 1 year ago
mudler 19dd6c7635 Debug 1 year ago
mudler 79cef86bec Adapt code 1 year ago
mudler c8c95ab46f fix: adapt golang bindings to api changes 1 year ago
Ettore Di Giacinto 3f63cc6b47
Golang bindings initial working version(#534)
* WIP

* Fix includes

* Try to fix linking issues

* Refinements

* allow to load MPT and llama models too

* cleanup, add example, add README
1 year ago