vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama : allow other bufts when overriding to CPU, add --no-repack option (#14990)

Browse source
This commit is contained in:
Diego Devesa 2025-07-31 09:11:34 -07:00 • committed by GitHub
parent e08a98826b
commit d6818d06a6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 39 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

1
common/common.h
View file

@ -359,6 +359,7 @@ struct common_params {
bool warmup = true; // warmup run
bool check_tensors = false; // validate tensor data
bool no_op_offload = false; // globally disable offload host tensor operations to device
bool no_extra_bufts = false; // disable extra buffer types (used for weight repacking)
bool single_turn = false; // single turn chat conversation