Oct 18 2 days ago

1. 23:29

   Cap llama.cpp prompt threads (n_threads_batch) at the container's cores

   Phoenixak99
   Verified signature

   25470c5
2. 23:21

   Top 3 passages to the LLM: faster answers, citations 100% in eval

   Phoenixak99
   Verified signature

   44c8bd7
3. 22:19

   v2: cited answers with hybrid retrieval + cross-encoder rerank, Qwen3-1.7B on CPU, retrieval trace

   Phoenixak99
   Verified signature

   a072368