Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/010-bug-compilation.yml
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	.github/ISSUE_TEMPLATE/019-bug-misc.yml
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
This commit is contained in:
Concedo
2025-12-28 23:47:55 +08:00
parent 58d8635827 07a0c4ba92
commit 0e26e4d354
15 changed files with 92 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+22 -7
View File
@@ -2019,7 +2019,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
if (llama_supports_rpc()) {
add_opt(common_arg(
{"--rpc"}, "SERVERS",
"comma separated list of RPC servers",
"comma separated list of RPC servers (host:port)",
[](common_params & params, const std::string & value) {
add_rpc_devices(value);
GGML_UNUSED(params);
@@ -2139,11 +2139,18 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_N_CPU_MOE_DRAFT"));
GGML_ASSERT(params.n_gpu_layers < 0); // string_format would need to be extended for a default >= 0
add_opt(common_arg(
{"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N",
string_format("max. number of layers to store in VRAM (default: %d)", params.n_gpu_layers),
[](common_params & params, int value) {
params.n_gpu_layers = value;
string_format("max. number of layers to store in VRAM, either an exact number, 'auto', or 'all' (default: %s)", params.n_gpu_layers == -1 ? "auto" : "all"),
[](common_params & params, const std::string & value) {
if (value == "auto") {
params.n_gpu_layers = -1;
} else if (value == "all") {
params.n_gpu_layers = -2;
} else {
params.n_gpu_layers = std::stoi(value);
}
if (!llama_supports_gpu_offload()) {
fprintf(stderr, "warning: no usable GPU found, --gpu-layers option will be ignored\n");
fprintf(stderr, "warning: one possible reason is that llama.cpp was compiled without GPU support\n");
@@ -3177,11 +3184,19 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.speculative.devices = parse_device_list(value);
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
GGML_ASSERT(params.speculative.n_gpu_layers < 0); // string_format would need to be extended for a default >= 0
add_opt(common_arg(
{"-ngld", "--gpu-layers-draft", "--n-gpu-layers-draft"}, "N",
"number of layers to store in VRAM for the draft model",
[](common_params & params, int value) {
params.speculative.n_gpu_layers = value;
string_format("max. number of draft model layers to store in VRAM, either an exact number, 'auto', or 'all' (default: %s)",
params.speculative.n_gpu_layers == -1 ? "auto" : "all"),
[](common_params & params, const std::string & value) {
if (value == "auto") {
params.speculative.n_gpu_layers = -1;
} else if (value == "all") {
params.speculative.n_gpu_layers = -2;
} else {
params.speculative.n_gpu_layers = std::stoi(value);
}
if (!llama_supports_gpu_offload()) {
fprintf(stderr, "warning: no usable GPU found, --gpu-layers-draft option will be ignored\n");
fprintf(stderr, "warning: one possible reason is that llama.cpp was compiled without GPU support\n");