roikoren755 737bfa3a43 [Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233) ...

Signed-off-by: Roi Koren <roik@nvidia.com>

2026-05-18 14:54:00 +03:00

..

kernels

[XPU] fix weight scale shape (#42725)

2026-05-17 16:55:10 +08:00

layers

[Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233)

2026-05-18 14:54:00 +03:00

model_loader

[Bugfix] Fix layerwise reload alias-buffer corruption (#42481)

2026-05-15 15:20:53 -07:00

models

[Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233)

2026-05-18 14:54:00 +03:00

offloader

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

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

warmup

[MoE Refactor] Move remaining experts classes to experts directory (#42334)

2026-05-12 09:19:46 -04:00

__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

[Quantization] add humming quantization kernel (#34556)

2026-04-24 09:29:44 -04:00

utils.py

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

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