KeithandSolitaryThinker c4824c7764 [bugfix] FP8: gate the ROCm _scaled_mm path on CDNA4 (gfx950) instead of the capability tuple (#1859) ...

Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>

2026-09-16 19:58:55 -07:00

..

__init__.py

[feat] add MXFP8 support on H3 (#1796)

2026-09-05 17:08:58 -07:00

absmax_fp8.py

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00

base_config.py

[feat]: NVFP4 text encoder for MiniMax H3 (#1837)

2026-09-12 18:31:59 -07:00

fp8_config.py

[bugfix] FP8: gate the ROCm _scaled_mm path on CDNA4 (gfx950) instead of the capability tuple (#1859)

2026-09-16 19:58:55 -07:00

fp8_qat_train_config.py

[feat] QAD 5090: FP8 QAT linear training (14/12) (#1464)

2026-06-19 01:03:51 -07:00

mxfp8_config.py

[feat] add MXFP8 support on H3 (#1796)

2026-09-05 17:08:58 -07:00

nvfp4_config.py

[feat] add MXFP8 support on H3 (#1796)

2026-09-05 17:08:58 -07:00

nvfp4_qat_config.py

[feat] Add Kandinsky5 QAD training pipeline: data preprocessing, QAT finetune, QAT-aware DMD distillation (#1601)

2026-07-26 02:59:21 -07:00

nvfp4_qat_train_config.py

[feat] Enable LTX-2 NVFP4 linear and attention QAT fine-tuning (#1626)

2026-07-26 02:19:34 -07:00