wwoosshh/GeulPUv2
Deterministic local LLM engine and debugger — run GGUF models on your own GPU, get bit-identical output, and record, replay and compare runs. Written in 글(geul).
GitHub repository with 6 stars and 1 forks.
Language: Python
Topics: cuda, debugger, deterministic, geul, gguf, llama, llm, llm-inference, local-llm, openai-api