Vadim Gimpelson 824058076c [PERF] Change GDN Attention State Layout from [N, HV, K, V] to [N, HV, V, K] (#33291) ...

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

2026-02-04 11:20:52 +00:00

..

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

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

linear_attn.py

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

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

mamba_mixer2.py

[MISC] Fix Tensor Parallelism for Quantized Mamba Models with n_groups=1 (#33257)

2026-02-03 15:10:31 -05:00

mamba_mixer.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

mamba_utils.py

[PERF] Change GDN Attention State Layout from [N, HV, K, V] to [N, HV, V, K] (#33291)

2026-02-04 11:20:52 +00:00

short_conv.py

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

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