feat: external PLE file loading (#31185)

* model : allow loading external PLE files

Assisted-by: Codex

* convert : add separate PLE exports

Assisted-by: Codex

* tests : fix PLE export test lint

Assisted-by: Codex

* model : make --ple an alias of --shard, allow multiple shard locations

Reuse the multi-shard loading path for external PLE files instead of a
separate option.

* --ple is an alias of --shard: both take a comma separated list and may
  be given more than once, and the shards may live anywhere
* metadata comes from the main file; numbered shards are still
  auto-discovered and strictly validated
* explicit files outside the discovered set are appended as extra shards,
  exempt from split.no and split.count checks
* -isnm/--ignore-shard-num-mismatch loads only the given files, in order,
  with no auto-discovery and no split metadata validation
* ple_path, path_ple and llama_model_loader::add_ple_file are removed;
  common_model_load() uses llama_model_load_from_splits for two or more
  paths
* common/fit.{h,cpp} take the shard path vector, so --fit and the router
  memory measurement load every shard

Assisted-by: GPT-6-Astra

* rm -isnm

* make sure to dedup paths

* rm test_convert_ple

* address comments

* allow ple shard to override tensor

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Piotr Wilkin (ilintar)andXuan Son Nguyen authored and GitHub committed 2026-11-09 19:41:01 +01:00
1 parent 9d340ec341
commit 5f490d7bfe
16 files changed
+317 -97

No files matched your search

+16 -3
View File
@@ -1258,13 +1258,13 @@ void common_fit_apply(common_params & params, llama_model_params & mparams, llam
cparams_dft.n_rs_seq = 0;
const common_fit_extra_model extra = {
/*.path_model =*/ params_dft.model.path.c_str(),
/*.paths_model =*/ params_dft.model.get_paths(),
/*.mparams =*/ &mparams_dft,
/*.cparams =*/ &cparams_dft,
/*.shares_model =*/ !has_draft, // an MTP context runs on the weights of the main model
};
common_fit_params(params.model.path.c_str(), &mparams, &cparams,
common_fit_params(params.model.get_paths(), &mparams, &cparams,
params.tensor_split,
params.tensor_buft_overrides.data(),
params.fit_params_target.data(),
@@ -1280,7 +1280,7 @@ common_init_result::common_init_result(common_params & params, bool model_only)
common_fit_apply(params, mparams, cparams);
llama_model * model = llama_model_load_from_file(params.model.path.c_str(), mparams);
llama_model * model = common_model_load(params.model.get_paths(), mparams);
if (model == NULL) {
return;
}
@@ -1722,6 +1722,19 @@ struct llama_model_params common_model_params_to_llama(common_params & params) {
return mparams;
}
struct llama_model * common_model_load(const std::vector<std::string> & paths, const struct llama_model_params & mparams) {
if (paths.size() == 1) {
return llama_model_load_from_file(paths[0].c_str(), mparams);
}
std::vector<const char *> c_paths;
c_paths.reserve(paths.size());
for (const auto & path : paths) {
c_paths.push_back(path.c_str());
}
return llama_model_load_from_splits(c_paths.data(), c_paths.size(), mparams);
}
struct llama_context_params common_context_params_to_llama(const common_params & params) {
auto cparams = llama_context_default_params();