3 people 33fe71a4d3 [AMD] Revert Mxfp4MoeBackend.TRITON_UNFUSED fallback (#46491) ...

Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>

2026-07-27 22:31:23 -05:00

..

kernels

[ROCm][Quark][6/N] Use MXFP4 linear kernel abstraction for aiter backend (#49348)

2026-07-27 21:35:57 -05:00

layers

[AMD] Revert Mxfp4MoeBackend.TRITON_UNFUSED fallback (#46491)

2026-07-27 22:31:23 -05:00

model_loader

[Bugfix] Wait for the linear bias before layerwise online processing (#49805)

2026-07-25 17:56:32 +00:00

models

[Feature] Add VidCom2 video token pruning (#47750)

2026-07-28 03:20:17 +00:00

offloader

Revert "[Platform] Replace torch.cuda.Event with torch.Event (#47140)" (#47668)

2026-07-06 14:18:33 +01:00

warmup

[Perf] Tune LL BF16 Router GEMM (#48774)

2026-07-27 10:25:37 -04:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

[Bugfix] Reject contradictory custom-op directives (#49134)

2026-07-26 08:42:14 -04:00

parameter.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

Remove more unnecessary load_weights methods (#47058)

2026-06-30 15:22:16 +01:00