Chenxi Yang 770cb2e1f8 Add CUTLASS FP8 MOE benchmark scripts and kernel config (#25302) ...

Signed-off-by: Chenxi Yang <cxyang@fb.com>
Co-authored-by: Chenxi Yang <cxyang@fb.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>

2025-10-03 13:35:54 -07:00

..

layers

Add CUTLASS FP8 MOE benchmark scripts and kernel config (#25302)

2025-10-03 13:35:54 -07:00

model_loader

[TPU] Deprecate xm.mark_step in favor of `torch_xla.sync (#25254)

2025-10-03 13:35:53 -07:00

models

Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512)

2025-10-03 13:35:54 -07:00

warmup

[Kernels] Support blocked fp8 quantization for compressed tensors MoE (#25219)

2025-10-03 13:35:54 -07:00

__init__.py

[V0 Deprecation] Remove V0 sampling metadata (#25345)

2025-10-03 13:35:53 -07:00

custom_op.py

[V0 deprecation] Deprecate V0 Neuron backend (#21159)

2025-09-06 16:15:18 -07:00

parameter.py

[OOT] Support sync_model_loading for OOT (#25126)

2025-09-19 05:41:53 +00:00

utils.py

[OOT] Support sync_model_loading for OOT (#25126)

2025-09-19 05:41:53 +00:00