jan/llamacpp-extension at 3982ed4c6f5ff3134d783e071ec80b70b5a4ddb5 - jan

History

Akarshan Biswas 3982ed4c6f

fix: Allow N-GPU Layers (NGL) to be set to 0 in llama.cpp (#5907 )

* fix: Allow N-GPU Layers (NGL) to be set to 0 in llama.cpp

The `n_gpu_layers` (NGL) setting in the llama.cpp extension was incorrectly preventing users from disabling GPU layers by automatically defaulting to 100 when set to 0.

This was caused by a condition that only pushed `cfg.n_gpu_layers` if it was greater than 0 (`cfg.n_gpu_layers > 0`).

This commit updates the condition to `cfg.n_gpu_layers >= 0`, allowing 0 to be a valid and accepted value for NGL. This ensures that users can effectively disable GPU offloading when desired.

* fix: default ngl

---------

Co-authored-by: Louis <louis@jan.ai>

2025-07-25 16:24:53 +05:30

src

fix: Allow N-GPU Layers (NGL) to be set to 0 in llama.cpp (#5907 )

2025-07-25 16:24:53 +05:30

package.json

Fix: engine unable to find dlls on when running on Windows (#5863 )

2025-07-22 20:05:24 +05:30

rolldown.config.mjs

Fix: engine unable to find dlls on when running on Windows (#5863 )

2025-07-22 20:05:24 +05:30

settings.json

fix: Persist 'Auto-Unload Old Models' setting in llama.cpp (#5906 )