Benjamin Chislett 8a680463fa [Bugfix] Fix NemotronH MTP + Chunked Prefill (#35447)

2026-03-17 07:07:33 +01:00

..

__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

[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (#33726)

2026-02-24 09:49:56 -08:00

layernorm_gated.py

replace with torch.cuda.device with with torch.accelerator.device_index (#36144)

2026-03-11 23:12:57 -07:00

mamba_ssm.py

[Bugfix] Fix NemotronH MTP + Chunked Prefill (#35447)

2026-03-17 07:07:33 +01:00

ssd_bmm.py

replace with torch.cuda.device with with torch.accelerator.device_index (#36144)

2026-03-11 23:12:57 -07:00

ssd_chunk_scan.py

[Kernel][Mamba] Optimize Mamba2 SSD prefill Triton kernels (#35397)

2026-03-04 19:47:17 +01:00

ssd_chunk_state.py

replace with torch.cuda.device with with torch.accelerator.device_index (#36144)

2026-03-11 23:12:57 -07:00

ssd_combined.py

[Kernel][Mamba] Optimize Mamba2 SSD prefill Triton kernels (#35397)

2026-03-04 19:47:17 +01:00

ssd_state_passing.py

replace with torch.cuda.device with with torch.accelerator.device_index (#36144)

2026-03-11 23:12:57 -07:00

triton_helpers.py

[Kernel][Mamba] Optimize Mamba2 SSD prefill Triton kernels (#35397)

2026-03-04 19:47:17 +01:00