Aryan KumarandAryan Kumar 4b4df1a94e [perf] Fused Q/K preconditioning + NVFP4 quantize for FA4 NVFP4 attention (bit-identical) (#2052) ...

Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>

2026-11-03 01:07:11 -08:00

..

__init__.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

abstract.py

[feat] Add H3 PDD/DMPDD training and packed Ref2VA preprocessing (#1984)

2026-10-20 11:15:57 -07:00

attn_qat_infer.py

[feat]: fp8 PV mode for the FA4-FP4 attention path (#1654)

2026-10-07 03:36:54 -07:00

attn_qat_train.py

[feat] Port NVFP4 QAT/QAD to modular train framework (#1619)

2026-07-18 15:01:09 -07:00

bsa_attn.py

[refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) (#1383)

2026-05-23 16:19:24 -07:00

flash_attn.py

[perf] Fused Q/K preconditioning + NVFP4 quantize for FA4 NVFP4 attention (bit-identical) (#2052)

2026-11-03 01:07:11 -08:00

fp4_dense_qat.py

[feat] Pika H3 Flex NVFP4 QAD training: calibration, QAD, FP4 attention and export (#2051)

2026-11-03 01:04:26 -08:00

fp4_vsa_qat.py

[feat]: shared FastH3 NVFP4 FP4-attention QAD recipe (OmniRef + V2 T2AV) (#1989)

2026-11-03 00:54:28 -08:00

minimax_h3_sparse_int8.py

[feat]: FastH3 on single RTX GPUs (#1919)

2026-10-06 11:37:01 -07:00

nabla.py

[feat] Add Kandinsky-5 T2V/I2V pipeline support (#1471)

2026-07-07 14:43:30 -07:00

sage_attn3.py

[Bugfix] QAD 5090: Torch.compile and other optimizations (15/12) (#1466)

2026-06-23 01:23:57 -07:00

sage_attn.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

sdpa.py

[feat] Add H3 PDD/DMPDD training and packed Ref2VA preprocessing (#1984)

2026-10-20 11:15:57 -07:00

sla.py

[misc] attention hot-path cleanup + denoising loop hoists (#1272)

2026-05-10 11:51:10 -07:00

video_sparse_attn_h3_probe.py

[misc] Move environment var reads into env registry and rename unprefixed variables (#1897)

2026-09-29 14:36:16 -07:00

video_sparse_attn_h3_scatter.py

[perf] FastH3 OmniRef: lossless speed-ups behind default-off switches (#1930)

2026-10-07 15:35:37 -07:00

video_sparse_attn_h3.py

[feat] Add H3 PDD/DMPDD training and packed Ref2VA preprocessing (#1984)

2026-10-20 11:15:57 -07:00

video_sparse_attn.py

[perf] Fuse VSA64 tile layout for SM100 inference (#1900)

2026-10-07 15:31:58 -07:00

vmoba.py

[feat] VSA for MiniMax H3: packed mixed-modality sparse attention (#1695)

2026-08-09 13:10:51 -07:00