docs: add FP8 hardware warning to Server/Desktop GPU/CPU

Re-bench 2/3/4-view sequential BF16 2026-08-30: Dense 4View 98.31% / MoE BEST 99.42% (bench_multiview_finals.json)

Update Model Card to match exact FP8-AdaRound and standard INT8 repo filenames

Add direct download links, accurate AdaRound FP8 vs INT8 quantization specs, and clean filenames

Update Model Card with verified Dense 4-View multi-angle benchmark results

Add CLI guide and quickstart instructions to Model Card

Update Multi-View benchmark table to mark Dense 4-View as Training in Progress

Clarify 4-View dedicated weights and add Dense 4-View Distilled specifications

Update Model Card with Dense Multi-View benchmarks and complete artifact catalog

Add Dense Mobile & Edge Suite with ONNX and LiteRT models

Add multi-photo (4 angles required) documentation and code examples

Update Model Card with PlantDetect naming and AdaRound-FP8 methodology

Initial commit: Model Card, Species Index (999 spp), and Model Architecture