realAsma 83d7623f2f Fixed FP8 fake quantization to use fp32 amax scaling; Added support for FP8 per-channel quantization (#381) ...

Signed-off-by: realAsma <akuriparambi@nvidia.com>

2025-09-30 01:56:11 +00:00

..

models.py

Update files on Github (#258)

2025-08-17 02:44:16 +05:30

onnx_export.py

…

quant_utils.py

…

quantize_common.py

Remove unused utilities for ModelOpt <0.29 MCore checkpoints (#322)

2025-09-16 12:45:44 -07:00

tensor_quant_common.py

Fixed FP8 fake quantization to use fp32 amax scaling; Added support for FP8 per-channel quantization (#381)

2025-09-30 01:56:11 +00:00

tensor_quantizer_common.py

…