Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/ui-build.yml
#	.github/workflows/ui-publish.yml
#	.github/workflows/ui-self-hosted.yml
#	CMakeLists.txt
#	app/CMakeLists.txt
#	app/llama.cpp
#	common/arg.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/sync-ggml.last
#	src/CMakeLists.txt
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/tests/test-deepseek-ocr.py
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-30 01:54:53 +08:00
55 changed files with 2443 additions and 251 deletions
+41 -46
View File
@@ -51,9 +51,6 @@
#define LLAMA_MAX_URL_LENGTH 2084 // Maximum URL Length in Chrome: 2083
extern const char * LICENSES[];
const char * LICENSES[] = {};
using json = nlohmann::ordered_json;
using namespace common_arg_utils;
@@ -344,9 +341,7 @@ struct handle_model_result {
};
static handle_model_result common_params_handle_model(struct common_params_model & model,
const std::string & bearer_token,
bool offline,
bool search_mtp = false) {
const common_download_opts & opts) {
handle_model_result result;
if (!model.docker_repo.empty()) {
@@ -358,10 +353,9 @@ static handle_model_result common_params_handle_model(struct common_params_model
model.hf_file = model.path;
model.path = "";
}
common_download_opts opts;
opts.bearer_token = bearer_token;
opts.offline = offline;
auto download_result = common_download_model(model, opts, true, search_mtp);
common_download_opts hf_opts = opts;
hf_opts.download_mmproj = true; // also look for mmproj when downloading hf model
auto download_result = common_download_model(model, hf_opts);
if (download_result.model_path.empty()) {
throw std::runtime_error("failed to download model from Hugging Face");
@@ -386,9 +380,6 @@ static handle_model_result common_params_handle_model(struct common_params_model
model.path = fs_get_cache_file(string_split<std::string>(f, '/').back());
}
common_download_opts opts;
opts.bearer_token = bearer_token;
opts.offline = offline;
auto download_result = common_download_model(model, opts);
if (download_result.model_path.empty()) {
throw std::runtime_error("failed to download model from " + model.url);
@@ -445,35 +436,49 @@ static bool parse_bool_value(const std::string & value) {
// CLI argument parsing functions
//
void common_params_handle_models(common_params & params, llama_example curr_ex) {
bool common_params_handle_models(common_params & params, llama_example curr_ex) {
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();
auto res = common_params_handle_model(params.model, params.hf_token, params.offline, spec_type_draft_mtp);
if (params.no_mmproj) {
params.mmproj = {};
} else if (res.found_mmproj && params.mmproj.path.empty() && params.mmproj.url.empty()) {
// optionally, handle mmproj model when -hf is specified
params.mmproj = res.mmproj;
}
// only download mmproj if the current example is using it
for (const auto & ex : mmproj_examples) {
if (curr_ex == ex) {
common_params_handle_model(params.mmproj, params.hf_token, params.offline);
break;
common_download_opts opts;
opts.bearer_token = params.hf_token;
opts.offline = params.offline;
opts.skip_download = params.skip_download;
opts.download_mtp = spec_type_draft_mtp;
try {
auto res = common_params_handle_model(params.model, opts);
if (params.no_mmproj) {
params.mmproj = {};
} else if (res.found_mmproj && params.mmproj.path.empty() && params.mmproj.url.empty()) {
// optionally, handle mmproj model when -hf is specified
params.mmproj = res.mmproj;
}
// only download mmproj if the current example is using it
for (const auto & ex : mmproj_examples) {
if (curr_ex == ex) {
common_params_handle_model(params.mmproj, opts);
break;
}
}
// when --spec-type mtp is set and no draft model was provided explicitly,
// fall back to the MTP head discovered alongside the -hf model
if (spec_type_draft_mtp && res.found_mtp &&
params.speculative.draft.mparams.path.empty() &&
params.speculative.draft.mparams.hf_repo.empty() &&
params.speculative.draft.mparams.url.empty()) {
params.speculative.draft.mparams.path = res.mtp.path;
}
common_params_handle_model(params.speculative.draft.mparams, opts);
common_params_handle_model(params.vocoder.model, opts);
return true;
} catch (const common_skip_download_exception &) {
return false;
} catch (const std::exception &) {
throw;
}
// when --spec-type mtp is set and no draft model was provided explicitly,
// fall back to the MTP head discovered alongside the -hf model
if (spec_type_draft_mtp && res.found_mtp &&
params.speculative.draft.mparams.path.empty() &&
params.speculative.draft.mparams.hf_repo.empty() &&
params.speculative.draft.mparams.url.empty()) {
params.speculative.draft.mparams.path = res.mtp.path;
}
common_params_handle_model(params.speculative.draft.mparams, params.hf_token, params.offline);
common_params_handle_model(params.vocoder.model, params.hf_token, params.offline);
}
static bool common_params_parse_ex(int argc, char ** argv, common_params_context & ctx_arg) {
@@ -1093,16 +1098,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
exit(0);
}
));
add_opt(common_arg(
{"--license"},
"show source code license and dependencies",
[](common_params &) {
for (int i = 0; LICENSES[i]; ++i) {
printf("%s\n", LICENSES[i]);
}
exit(0);
}
));
add_opt(common_arg(
{"-cl", "--cache-list"},
"show list of models in cache",