llm
an archive of posts with this tag
-
llama.cpp로 로컬 LLM 띄우기 — 빌드, 모델 다운로드, 서빙, 벤치마크
GGUF 모델을 내 장비에서 직접 돌리기 위한 llama.cpp 최소 워크플로우. cmake 빌드부터 OpenAI 호환 서버, llama-bench까지.
-
Pydantic with llm.with_structured_output — pitfalls and safeguards
Combining Pydantic models with LangChain's with_structured_output cleanly — avoiding prompt collisions, validation errors, and runaway evaluation loops.