russell@unturf.com 80b26e82b6 ml-inference scan: vllm-0001 LoRA convert_mapping list.index O(B*L); ollama+langchain CLEAN ... vllm-0001: punica_wrapper/utils.py convert_mapping() calls lora_index_to_id.index(x) per token in batch — O(B*L) where B=batch_size, L=loaded_loras. Code has "TODO index can be slow" comment. Fix: pre-build dict for O(1) lookup. 7x at B=2000/L=64. Ollama: all slices.Contains on bounded slices (1-8 items). LangChain: orchestration code, all membership bounded by k param.		2026-03-30 16:41:47 -04:00
..
CLEAN.md	ml-inference scan: vllm-0001 LoRA convert_mapping list.index O(B*L); ollama+langchain CLEAN	2026-03-30 16:41:47 -04:00