Thien Tran d9105ea800 [Qwen3.8-Flash-Next] Remove torch.compile for NVIDIA implementation (#55272) ...

Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>

2026-09-06 21:57:56 -07:00

..

gdn

[Qwen3.8-Flash-Next] Remove torch.compile for NVIDIA implementation (#55272)

2026-09-06 21:57:56 -07:00

linear

[Kernel] Remove unused fake implementation (#55535)

2026-09-06 17:54:32 -07:00

ops

[Kernel] Remove unused fake implementation (#55535)

2026-09-06 17:54:32 -07:00

__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] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

mamba_mixer2.py

[Kernel] Remove unused fake implementation (#55535)

2026-09-06 17:54:32 -07:00

mamba_mixer.py

[Kernel] Remove unused fake implementation (#55535)

2026-09-06 17:54:32 -07:00

mamba_utils.py

[Mamba] Add FlashInfer ReplaySSM backend (#52506)

2026-09-01 10:26:43 -04:00

short_conv.py

[Kernel] Remove unused fake implementation (#55535)

2026-09-06 17:54:32 -07:00