Language Models
stas00/ml-engineering🔥 active
Machine Learning Engineering Open Book
PythonCC-BY-SA-4.0updated Nov 4, 2026
LLM inference engine from scratch — paged KV cache, continuous batching, chunked prefill, prefix caching, speculative decoding, CUDA graph, tensor parallelism, OpenAI-compatible serving
$ git clone https://github.com/psmarter/mini-infer.gitMachine Learning Engineering Open Book
Build a modern LLM from scratch. Every line commented. Explained like we are five.
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
Data from GitHub · snapshot Nov 9, 2026