Add full-encoder MXFP8 RTN FLUX.2 model and tested inference examples

54daaf9 verified 3 days ago

392 Bytes

{
  "auto_round_commit": "8869842f9741538ea729849d5c23592bdb605e61",
  "scheme": "MXFP8",
  "iters": 0,
  "disable_opt_rtn": true,
  "encoder_coverage": [
    "language_model.model.layers",
    "vision_tower.transformer.layers",
    "multi_modal_projector"
  ],
  "transformer": "/home/changwa1/FLUX.2-dev-MXFP8-RTN-blocks-only/transformer",
  "visual_task_validation": "not yet performed"
}

	{
	"auto_round_commit": "8869842f9741538ea729849d5c23592bdb605e61",
	"scheme": "MXFP8",
	"iters": 0,
	"disable_opt_rtn": true,
	"encoder_coverage": [
	"language_model.model.layers",
	"vision_tower.transformer.layers",
	"multi_modal_projector"
	],
	"transformer": "/home/changwa1/FLUX.2-dev-MXFP8-RTN-blocks-only/transformer",
	"visual_task_validation": "not yet performed"
	}