Add low vram mode on llama cpp (#3076)

This commit is contained in:
Gabriel Pena 2023-07-12 11:05:13 -03:00 committed by GitHub
parent 180420d2c9
commit eedb3bf023
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 5 additions and 0 deletions

View file

@ -49,6 +49,7 @@ class LlamaCppModel:
'n_batch': shared.args.n_batch,
'use_mmap': not shared.args.no_mmap,
'use_mlock': shared.args.mlock,
'low_vram': shared.args.low_vram,
'n_gpu_layers': shared.args.n_gpu_layers
}