Thomas Parnell e0c910bb89 [Hybrid] [Kernel] Fix chunk scan kernel when BLOCK_SIZE_DSTATE > 128 (#28295) ...

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>

2025-11-14 22:55:42 +00:00

..

ops

[Hybrid] [Kernel] Fix chunk scan kernel when BLOCK_SIZE_DSTATE > 128 (#28295)

2025-11-14 22:55:42 +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

[Misc] Refactor get_kv_cache_spec into AttentionLayerBase (#26587)

2025-10-18 13:51:21 +00:00

linear_attn.py

Fix MiniMax-M2 rmsnorm precision and remove useless code (#27627)

2025-10-29 21:01:05 +08:00

mamba_mixer2.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

mamba_mixer.py

[V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377)

2025-11-02 04:16:23 -08:00

mamba_utils.py

[Model] Introduce Kimi Linear to vLLM (#27809)

2025-10-30 21:02:27 +08:00

short_conv.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00