Artem Perevedentsev bb6047db13 [Model][Perf] Enable checkpoints prefetching for Lustre FS by default (#39422) ...

Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>

2026-04-10 00:47:59 +00:00

..

reload

[Bug] Add e_score_correction_bias to SKIP_TENSORS (#38746)

2026-04-02 21:15:05 -07:00

__init__.py

…

base_loader.py

[CI]revert initialize_model context manager (#38426)

2026-03-28 16:56:50 +00:00

bitsandbytes_loader.py

…

default_loader.py

…

dummy_loader.py

[Quantization] Consolidate dummy format logic into DummyModelLoader (#38637)

2026-03-31 22:20:45 +00:00

ep_weight_filter.py

…

gguf_loader.py

[Model][Quantization] Add GGUF support for MiniMax-M2.1 (#36965)

2026-03-30 14:24:06 +08:00

runai_streamer_loader.py

…

sharded_state_loader.py

…

tensorizer_loader.py

…

tensorizer.py

…

utils.py

…

weight_utils.py

[Model][Perf] Enable checkpoints prefetching for Lustre FS by default (#39422)

2026-04-10 00:47:59 +00:00