Joe RowellandRobert Shaw c8d2f3cb14 [Bugfix] compressed-tensors: allow int8 grouped WNA16 MoE on Marlin (#47154) ...

Signed-off-by: Joe Rowell <joerowell4@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

2026-06-30 12:50:46 -07:00

..

kernels

[CPU][RISC-V] Add RVV path for W4A8 INT4 GEMM (#45269)

2026-06-25 08:18:10 +00:00

layers

[Bugfix] compressed-tensors: allow int8 grouped WNA16 MoE on Marlin (#47154)

2026-06-30 12:50:46 -07:00

model_loader

Remove more unnecessary load_weights methods (#47058)

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

models

Add Medusa speculative decoding e2e test (#41396)

2026-06-30 18:02:22 +00:00

offloader

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

2026-06-30 08:39:59 -07:00

warmup

[Feat][1/N] CuTeDSL warmup infrastructure, FA4 MLA (#46182)

2026-06-30 12:17:34 -07:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

Add ability to replace oot ops when using lora (#37181)

2026-03-16 18:04:15 -07:00

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