Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	CODEOWNERS
#	README.md
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q8_0_f32.cl
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_id_vec.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_q_acc.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/quantize_q8.wgsl
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-sampling.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-06-24 23:28:21 +08:00
parent 19064083bd 51eae8cfca
commit 579229d157
156 changed files with 4484 additions and 2930 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+14 -5
View File
@@ -302,6 +302,8 @@ static handle_model_result common_params_handle_model(struct common_params_model
const common_download_opts & opts) {
handle_model_result result;
// TODO @ngxson : refactor this into a new common_model_download_context
if (!model.docker_repo.empty()) {
model.path = common_docker_resolve_model(model.docker_repo);
} else if (!model.hf_repo.empty()) {
@@ -397,7 +399,7 @@ static bool parse_bool_value(const std::string & value) {
// CLI argument parsing functions
//
bool common_params_handle_models(common_params & params, llama_example curr_ex) {
bool common_params_handle_models(common_params & params, llama_example curr_ex, const common_params_handle_models_params & handle_params) {
const bool spec_type_draft_mtp = std::find(params.speculative.types.begin(),
params.speculative.types.end(),
COMMON_SPECULATIVE_TYPE_DRAFT_MTP) != params.speculative.types.end();
@@ -408,6 +410,11 @@ bool common_params_handle_models(common_params & params, llama_example curr_ex)
opts.skip_download = params.skip_download;
opts.download_mtp = spec_type_draft_mtp;
opts.download_mmproj = !params.no_mmproj && params.mmproj.path.empty() && params.mmproj.url.empty();
opts.preset_only = handle_params.preset_only;
if (handle_params.callback) {
opts.callback = handle_params.callback;
}
// sub-models (draft, mmproj, vocoder) are explicitly specified by the user,
// so we should not auto-discover mtp/mmproj siblings for them
@@ -585,17 +592,19 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
throw std::invalid_argument("error: --prompt-cache-all not supported in interactive mode yet\n");
}
// export_graph_ops loads only metadata
const bool skip_model_download = ctx_arg.ex == LLAMA_EXAMPLE_EXPORT_GRAPH_OPS;
const bool skip_model_download =
// server will call common_params_handle_models() later, so we skip it here
ctx_arg.ex == LLAMA_EXAMPLE_SERVER ||
// export_graph_ops loads only metadata
ctx_arg.ex == LLAMA_EXAMPLE_EXPORT_GRAPH_OPS;
if (!skip_model_download) {
// handle model and download
common_params_handle_models(params, ctx_arg.ex);
common_params_handle_models(params, ctx_arg.ex, {});
// model is required (except for server)
// TODO @ngxson : maybe show a list of available models in CLI in this case
if (params.model.path.empty()
&& ctx_arg.ex != LLAMA_EXAMPLE_SERVER
&& !params.usage
&& !params.completion) {
throw std::invalid_argument("error: --model is required\n");