Aryan KumarandAryan Kumar d954fad9ec [perf] MiniMax H3: faster FP4 attention padding, uint8 VAE pixel path and cuDNN FP4 GEMMs (#2046) ...

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

2026-11-01 22:23:10 -08:00

..

__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

[perf] FP8: fuse the dynamic activation quantization into Triton kernels (#1861)

2026-10-07 03:20:04 -07:00

fp8_kernels.py

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

2026-10-06 11:37:01 -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

fp8_quant_kernels.py

[perf] FP8: fuse the dynamic activation quantization into Triton kernels (#1861)

2026-10-07 03:20:04 -07:00

mxfp8_config.py

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

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

nvfp4_config.py

[perf] MiniMax H3: faster FP4 attention padding, uint8 VAE pixel path and cuDNN FP4 GEMMs (#2046)

2026-11-01 22:23:10 -08:00

nvfp4_dequant.py

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

2026-10-06 11:37:01 -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