Woosuk Kwon 96de8bb389 [MoE] Free unused MXFP4 scales in OAI Triton Backend (#46549) ...

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>

2026-06-24 00:06:41 -07:00

..

kernels

[Kernel] Add FlashInferCutedslMxfp8LinearKernel (cute-dsl mm_mxfp8) (#46393)

2026-06-23 12:45:49 -07:00

layers

[MoE] Free unused MXFP4 scales in OAI Triton Backend (#46549)

2026-06-24 00:06:41 -07:00

model_loader

Deprecate old FP8 online MoE quantization class (#44514)

2026-06-23 11:53:38 -07:00

models

[Bugfix] Fix NemotronLayerNorm1P hardcoded cuda device type (#46495)

2026-06-24 13:21:02 +08:00

offloader

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

warmup

Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)

2026-06-22 11:54:14 -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

[Bugfix][Rocm]Aiter MoE re-uses existing tensor addresses after weight update. (#40390)

2026-05-06 10:32:26 +00:00