4 people f51193b9ae [Kernel][Mamba] Fused-kernel support for align-mode DS-conv state migration with num_accepted_tokens > 1 (#49291) ...

Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

2026-07-29 18:54:52 +08:00

..

cpu

[CPU][Spec Decode] Optimize GDN conv path for speculative decoding (#48577)

2026-07-27 06:20:14 +00:00

__init__.py

Tuning script and configs for Triton Mamba SSU kernel (#43083)

2026-05-24 20:12:44 +03:00

test_causal_conv1d.py

[Hardware][CPU] Enable granite-4 model on cpu (#47641)

2026-07-20 06:15:16 +00:00

test_cpu_short_conv.py

[CPU][Bugfix] Fix flaky ShortConv prefill test on ARM (uninitialized weights) (#47848)

2026-07-07 18:20:09 -07:00

test_gdn_forward_core_split.py

[Refactor] Move fla to third party (#48500)

2026-07-16 19:22:36 +01:00

test_gdn_prefill_cutedsl.py

[CI] stabilize GDN prefill CuTeDSL test (#49388)

2026-07-22 09:03:46 -07:00

test_mamba_mixer2.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

test_mamba_ssm_configs.py

Tuning script and configs for Triton Mamba SSU kernel (#43083)

2026-05-24 20:12:44 +03:00

test_mamba_ssm_ssd.py

[Kernel][Test] Make kernel tests for mamba dual-HW (CUDA + XPU) (#42736)

2026-06-08 08:22:47 +08:00

test_mamba_ssm.py

[Hardware][CPU] Enable granite-4 model on cpu (#47641)

2026-07-20 06:15:16 +00:00

test_precopy_mamba_align.py

[Kernel][Mamba] Fused-kernel support for align-mode DS-conv state migration with num_accepted_tokens > 1 (#49291)

2026-07-29 18:54:52 +08:00

test_replayssm_prefill_decode_equivalence_mamba2.py

[Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 standard decode (#48018)

2026-07-24 09:39:49 -07:00

test_replayssm_standard_decode_mamba2.py

[Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 standard decode (#48018)

2026-07-24 09:39:49 -07:00

test_ssu_dispatch.py

[Misc] Replace mamba_type string literals with MambaAttentionBackendEnum (#41188)

2026-05-11 03:59:36 +00:00

utils.py

[Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 standard decode (#48018)

2026-07-24 09:39:49 -07:00