CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Document the new max GPU layers default in help (#15771)

Browse Source 
This is a key change, just letting users know.

Signed-off-by: Eric Curtin <ericcurtin17@gmail.com>
This commit is contained in:
Eric Curtin
2025-09-04 10:49:44 +01:00
committed by GitHub
parent 0a1b3982cd
commit badb80cadb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/arg.cpp
View File

@@ -2466,7 +2466,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_N_CPU_MOE_DRAFT")); ).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_N_CPU_MOE_DRAFT"));
add_opt(common_arg( add_opt(common_arg(
{"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N", {"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N",
"number of layers to store in VRAM", string_format("max. number of layers to store in VRAM (default: %d)", params.n_gpu_layers),
[](common_params & params, int value) { [](common_params & params, int value) {
params.n_gpu_layers = value; params.n_gpu_layers = value;
if (!llama_supports_gpu_offload()) { if (!llama_supports_gpu_offload()) {