mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 26 Packages Projects Releases Wiki Activity

tests: allow exporting graph ops from HF file without downloading weights (#21182)

Browse Source 
* tests: allow exporting graph ops from HF file without downloading weights

* use unique_ptr for llama_context in HF metadata case

* fix missing non-required tensors falling back to type f32

* use unique pointers where possible

* use no_alloc instead of fixing f32 fallback

* fix missing space
This commit is contained in:
Ruben Ortlam
2026-04-02 18:19:20 +02:00
committed by GitHub
parent 63f8fe0ef4
commit 5803c8d115
7 changed files with 169 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+5 -3
View File
@@ -537,9 +537,11 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
} catch (const std::exception & e) {
LOG_WRN("HF cache migration failed: %s\n", e.what());
}
// export_graph_ops loads only metadata
const bool skip_model_download = ctx_arg.ex == LLAMA_EXAMPLE_EXPORT_GRAPH_OPS;
// maybe handle remote preset
if (!params.model.hf_repo.empty()) {
if (!params.model.hf_repo.empty() && !skip_model_download) {
std::string cli_hf_repo = params.model.hf_repo;
bool has_preset = common_params_handle_remote_preset(params, ctx_arg.ex);
@@ -570,7 +572,7 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
}
// handle model and download
{
if (!skip_model_download) {
auto res = common_params_handle_model(params.model, params.hf_token, params.offline);
if (params.no_mmproj) {
params.mmproj = {};
@@ -591,7 +593,7 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
// 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) {
if (params.model.path.empty() && ctx_arg.ex != LLAMA_EXAMPLE_SERVER && !skip_model_download && !params.usage && !params.completion) {
throw std::invalid_argument("error: --model is required\n");
}