Fix Docker build OOM; fix missing bm25_prefilter in Streamlit; update docs

Add bm25 prefilter stage; unify candidates cache; validate reasoning quality

Respect --limit; LLM streaming heartbeat

Cache-first model loading for zero-network ranking

Add CPU threading, T1-only LLM polish, experiment script

Docker: pre-download all models at build for offline ranking + docs

Add full pipeline, submission & reasoning support

Add ONNX granite/reranker and compute config

Add JD parsing, central config, checkpoints & LLM

Updated

update