Chih-Chieh Yang b690e34824

[Model] Mamba2 preallocate SSM output tensor to avoid d2d copy overhead (#21075) ...

Signed-off-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>

2025-08-02 01:59:34 -07:00

..

__init__.py

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

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

causal_conv1d.py

[BugFix] fix 3 issues: (1) using metadata for causal-conv1d, (2) indexing overflow in v1 vLLM, and (3) init_states in v0 (#20838)

2025-07-15 16:08:26 -04:00

layernorm_gated.py

[Model] Replace Mamba2 RMSNorm Gated with Fused Triton Kernel (#20839)

2025-07-25 06:49:36 -07:00

mamba_ssm.py

[Model] Mamba2 preallocate SSM output tensor to avoid d2d copy overhead (#21075)

2025-08-02 01:59:34 -07:00

ssd_bmm.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

ssd_chunk_scan.py

[Model] Mamba2 preallocate SSM output tensor to avoid d2d copy overhead (#21075)

2025-08-02 01:59:34 -07:00

ssd_chunk_state.py

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

ssd_combined.py

[Model] Mamba2 preallocate SSM output tensor to avoid d2d copy overhead (#21075)

2025-08-02 01:59:34 -07:00

ssd_state_passing.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00