* 【Hackathon 10th Spring No.32】Unit test for load_weight_utils.py
* [CI]【Hackathon 10th Spring No.32】rewrite load_weight_utils unit test
* [CI]【Hackathon 10th Spring No.32】improve load_weight_utils coverage to 83%
- Add test_load_ep_checkpoint_basic: exercises EP checkpoint loading with minimal fixture
- Add test_composite_ep_branch: covers EP path in load_composite_checkpoint
- Add test_get_weight_iterator_unordered: covers unordered sharded safetensors path
* [CI]【Hackathon 10th Spring No.32】align load_weight_utils test with gold standard (tmp_path, split tests)
* [CI]【Hackathon 10th Spring No.32】add coverage tests for load_weight_utils
- Add test_is_layers_grouped: test layers_are_grouped() with grouped, interleaved, and no-layer keys
- Add test_save_model_bf16_cache: exercise save_model decorator with is_checkpoint_bf16=True
- Add test_composite_checkpoint_ep: test load_composite_checkpoint use_ep=True branch
- Add test_composite_checkpoint_rank_mismatch: test tp_size != rank_dirs ValueError
- Add test_composite_checkpoint_kv_quant: test float8_e4m3fn kv_cache path
- Add __main__ block for direct execution
* [CI]【Hackathon 10th Spring No.32】raise load_weight_utils test delta
* [CI]【Hackathon 10th Spring No.32】cover TP sequence-parallel MoE load branches
* test: add load_reordered_experts, pre-sharded, and empty-state tests
---------
Co-authored-by: cloudforge1 <cloudforge1@users.noreply.github.com>
cloudforge1