yangzhuxinyzx 3592a85770 [Model Loader] Admit direct reads by storage and memory capacity ...

Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

2026-10-03 08:07:30 +08:00

..

fastsafetensors_loader

…

instanttensor_loader

…

runai_streamer_loader

Fix RunAI streamer tensor buffer reuse during weight loading (#43464)

2026-05-27 19:16:52 -07:00

tensorizer_loader

[Bugfix][Worker] Keep dummy-run positions inside max_model_len

2026-09-21 23:04:02 +02:00

__init__.py

…

test_direct_io.py

[Model Loader] Admit direct reads by storage and memory capacity

2026-10-03 08:07:30 +08:00

test_ep_weight_filter.py

[Perf][Loader] Skip checkpoint tensors a model does not load before reading them

2026-09-21 23:15:27 +02:00

test_modelexpress_loader.py

[Core] Add native ModelExpress load format (#43105)

2026-05-21 16:05:01 -04:00

test_registry.py

…

test_reload.py

[Bugfix] Fix layerwise reload alias-buffer corruption (#42481)

2026-05-15 15:20:53 -07:00

test_safetensors_index_filter.py

fix(loader): only filter by index when a shard stores unindexed tensors

2026-08-29 15:19:29 -07:00

test_sharded_state_loader.py

…