Refresh EAGLE-3 references for the thinking-aware v2 head (2026-07-24 retrain); concurrency section re-measured (501/878/1017 tok/s, ITL 6.2-7.6ms)

Add Performance-under-load section (concurrency sweep, GuideLLM real-data)

Embed multi-bench quality chart

GPQA-diamond 81.3 at 32k thinking budget (embargo lifted: 16k-truncated runs invalidated; full methodology in provenance)

Qualify spec recommendation: eagle3 for short-context, ngram for long-document summarize (measured)

Add EAGLE-3 draft head to family (chooser row, links; FP8 card: eagle3 as recommended spec)

Embed family charts in the artifact chooser

Style pass: em-dash cleanup in new sections

Split speed from quality evals; add artifact chooser + download snippet

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload folder using huggingface_hub