vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

added mmq launch flag

Browse source
This commit is contained in:
Concedo 2023-08-01 17:57:13 +08:00
parent e221843147
commit 46682e5cb3
4 changed files with 27 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

2
gpttype_adapter.cpp
View file

@ -466,7 +466,7 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
llama_ctx_params.seed = -1;
llama_ctx_params.f16_kv = inputs.f16_kv;
llama_ctx_params.low_vram = inputs.low_vram;
llama_ctx_params.mul_mat_q = true;
llama_ctx_params.mul_mat_q = inputs.use_mmq;
llama_ctx_params.logits_all = false;
llama_ctx_params.use_mmap = inputs.use_mmap;
llama_ctx_params.use_mlock = inputs.use_mlock;