vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix other examples

Browse source
This commit is contained in:
slaren 2024-11-25 18:08:33 +01:00
parent d6cf9186f5
commit acf43cc178
2 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/server.cpp
View file

@ -692,6 +692,7 @@ struct server_context {
auto params_dft = params_base; auto params_dft = params_base;
params_dft.devices = params_base.speculative.devices;
params_dft.model = params_base.speculative.model; params_dft.model = params_base.speculative.model;
params_dft.n_ctx = params_base.speculative.n_ctx; params_dft.n_ctx = params_base.speculative.n_ctx;
params_dft.n_gpu_layers = params_base.speculative.n_gpu_layers; params_dft.n_gpu_layers = params_base.speculative.n_gpu_layers;

1
examples/speculative-simple/speculative-simple.cpp
View file

@ -46,6 +46,7 @@ int main(int argc, char ** argv) {
ctx_tgt = llama_init_tgt.context; ctx_tgt = llama_init_tgt.context;
// load the draft model // load the draft model
params.devices = params.speculative.devices;
params.model = params.speculative.model; params.model = params.speculative.model;
params.n_ctx = params.speculative.n_ctx; params.n_ctx = params.speculative.n_ctx;
params.n_batch = params.speculative.n_ctx > 0 ? params.speculative.n_ctx : params.n_batch; params.n_batch = params.speculative.n_ctx > 0 ? params.speculative.n_ctx : params.n_batch;