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

+20
View File
@@ -245,6 +245,26 @@ static void test(void) {
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.model.path == "model_file.gguf");
{
auto parse_shards = [&list_str_to_char](std::vector<std::string> args) {
common_params shard_params;
args.insert(args.begin(), {"binary_name", "-m", "model_file.gguf"});
assert(common_params_parse(args.size(), list_str_to_char(args).data(), shard_params, LLAMA_EXAMPLE_COMMON));
auto paths = shard_params.model.get_paths();
assert(paths.front() == "model_file.gguf");
return std::vector<std::string>(paths.begin() + 1, paths.end());
};
assert(parse_shards({"--shard", "a.gguf"}) == std::vector<std::string>({"a.gguf"}));
const std::vector<std::string> two = {"a.gguf", "b.gguf"};
assert(parse_shards({"--shard", "a.gguf", "--shard", "b.gguf"}) == two);
assert(parse_shards({"--shard", "a.gguf,b.gguf"}) == two);
const std::vector<std::string> three = {"a.gguf", "b.gguf", "c.gguf"};
assert(parse_shards({"--shard", "a.gguf,b.gguf", "--shard", "c.gguf"}) == three);
assert(parse_shards({"--shard", "a.gguf", "--shard", "b.gguf", "--shard", "c.gguf"}) == three);
assert(parse_shards({"--ple", "p.gguf"}) == parse_shards({"--shard", "p.gguf"}));
assert(parse_shards({"--shard", "model_file.gguf,a.gguf,b.gguf,a.gguf"}) == two);
}
argv = {"binary_name", "-t", "1234"};
assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
assert(params.cpuparams.n_threads == 1234);