Tao He dd6a910aac [Bugfix][Qwen3-Next] fixes the varlen issue in qwen3-next's MTP implementation. (#24957) ...

Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>

2025-09-17 21:59:09 +08:00

..

ops

[Bugfix][Qwen3-Next] fixes the varlen issue in qwen3-next's MTP implementation. (#24957)

2025-09-17 21:59:09 +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

[Attention] Unify mamba and attention backend selection (#23171)

2025-08-25 09:09:36 +00:00

linear_attn.py

[Model] Remove useless code from MiniMax implementation (#23982)

2025-09-03 11:27:04 +00:00

mamba2_metadata.py

[Model] Clean up and simplify Mamba2 Metadata Usage in both V0 and V1 (#24331)

2025-09-16 14:53:43 +00:00

mamba_mixer2.py

[Model] Clean up and simplify Mamba2 Metadata Usage in both V0 and V1 (#24331)

2025-09-16 14:53:43 +00:00

mamba_mixer.py

[Attention] Unify mamba and attention backend selection (#23171)

2025-08-25 09:09:36 +00:00

mamba_utils.py

Add the support for the qwen3 next model (a hybrid attention model). (#24526)

2025-09-11 15:32:09 +08:00

short_conv.py

[Attention] Unify mamba and attention backend selection (#23171)

2025-08-25 09:09:36 +00:00