Vadim Gimpelson 604b9eaec5 [BUGFIX] Fix accuracy regression for NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 with TP>1 (#34476) ...

Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>

2026-02-14 23:25:17 -08:00

..

ops

[Performance] Tune Mamba selective scan kernel for B200 (#32873)

2026-01-26 05:56:54 -08:00

__init__.py

[Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (#7651)

2024-08-28 15:06:52 -07:00

abstract.py

[MODEL] Adding Support for Qwen3.5 Models (#34110)

2026-02-09 21:12:58 +08:00

linear_attn.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

mamba_mixer2.py

[BUGFIX] Fix accuracy regression for NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 with TP>1 (#34476)

2026-02-14 23:25:17 -08:00

mamba_mixer.py

[PluggableLayer][3/N] Apply PluggableLayer to mamba layers. (#33660)

2026-02-07 05:26:05 -08:00

mamba_utils.py

[Bugfix] Fix mamba state dtype setting for Qwen3-Next and Qwen3.5 (#34489)

2026-02-12 22:48:42 -08:00

short_conv.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00