3 people b538d807ff [Bugfix][MRV2] Keep GDN prefill checkpoint metadata local to each cache group (#59536) ...

Signed-off-by: Jingqiao Zhang <ai-jz@users.noreply.github.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jingqiao Zhang <ai-jz@users.noreply.github.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>

2026-10-01 22:59:15 +08:00

..

gdn

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

linear

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

ops

[Mamba] Add FlashInfer ReplaySSM support for MTP (#52928)

2026-09-30 21:41:17 +00:00

__init__.py

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

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

abstract.py

[Mamba] Add FlashInfer ReplaySSM support for MTP (#52928)

2026-09-30 21:41:17 +00:00

checkpoint.py

[Bugfix][MRV2] Keep GDN prefill checkpoint metadata local to each cache group (#59536)

2026-10-01 22:59:15 +08:00

kda_checkpoint.py

[Core][KDA] Generalize Mamba prefill checkpoint builder and exporter (#57783)

2026-09-21 04:46:11 +00:00

mamba_mixer2.py

[Core] Remove deprecated mamba_cache_mode "all" (#58997)

2026-10-01 02:59:37 -07:00

mamba_mixer.py

[Core] Remove deprecated mamba_cache_mode "all" (#58997)

2026-10-01 02:59:37 -07:00

mamba_utils.py

[Mamba] Add FlashInfer ReplaySSM support for MTP (#52928)

2026-09-30 21:41:17 +00:00

short_conv.py

[Kernel] Remove unused fake implementation (#55535)

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