Implementation for MatMul-free LM.
Pocket Flow: Codebase to Tutorial
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
Minimal reproduction of OneRec