docs: note sub_10 only training following chayan

docs: replace KNN references with generic predictor terminology

docs: embed leaderboard screenshot in README

docs: add RouterArena leaderboard screenshot

docs: use paper title

docs: add paper link and bibtex citation

docs: change example query to Solve this integral

fix: correct cost display unit to per-query dollar amount

docs: show estimated quality and cost in example output

docs: use generic predictor terminology in training output

feat: add training progress prints to from_training_data()

docs: simplify README, remove GPU/CPU examples

docs: add lambda parameter documentation with examples

fix: update vllm serve comment to --runner pooling

fix: use --runner pooling instead of --task embed for vllm serve

Fix vllm serve command for different versions

Add vLLM server mode: start once, route from anywhere

vLLM-based route_text(), uv install guide, complete runnable examples

Fix: use transformers AutoModel instead of sentence_transformers for Qwen3 compatibility

Fix Quick Start: complete runnable example with embedding generation

Fix Quick Start: use snapshot_download for proper import

Initial release: R2-Router (#1 on RouterArena)

initial commit