vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-11 09:34:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: some fields in cparams_draft

Browse source
This commit is contained in:
DeEMO 2025-06-27 06:07:47 +00:00
parent 2e8e42a5ad
commit d248f3c40e
2 changed files with 13 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

5
common/arg.cpp
View file

@ -1555,13 +1555,14 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
{"-ngld", "--gpu-layers-draft", "--n-gpu-layers-draft"}, "N",
"number of layers to store in VRAM for the draft model",
[](gpt_params & params, int value) {
params.n_gpu_layers_draft = value;
params.n_gpu_layers_draft = value; // TODO: remove
params.speculative.n_gpu_layers = value;
if (!llama_supports_gpu_offload()) {
fprintf(stderr, "warning: not compiled with GPU offload support, --gpu-layers-draft option will be ignored\n");
fprintf(stderr, "warning: see main README.md for information on enabling GPU BLAS support\n");
}
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE}));
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER}));
add_opt(llama_arg(
{"-sm", "--split-mode"}, "{none,layer,row}",
"how to split the model across multiple GPUs, one of:\n"