Add ConvRot file-level format metadata to prepared checkpoints

Add quantization_format=int8_convrot and convrot_format=comfy_quant_v1. Preserve every tensor payload, dtype, shape and filename. Verified identical quantization detection, maps and runtime tensors; detection and conversion each perform zero per-layer comfy_quant JSON reads with the header markers.

minimax_h3/minimax_h3_video_vae_int8_convrot.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a2c8c73583c86e4f41cdcce3a6ad0ea562987bc0bf3d60a0cef5f5c8e60c0e
-size 2811065184
+oid sha256:0cb8161a12166fb049a2c1295e6a4833fdc571effdab9ac0ed074b10f2d6646d
+size 2811065256