🏆 #2,351 overall#549 of 601 in Language Models

psmarter /mini-infer

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.git
GitHub social preview for psmarter/mini-infer
Stars
220
220
Forks
11
11
Language
Python
License
MIT
Created
Dec 30, 2025
0.9 years old
Last push
Apr 24, 2026

Categories

GitHub topics

More in Language Models

Language Models

stas00/ml-engineering🔥 active

Machine Learning Engineering Open Book

PythonCC-BY-SA-4.0updated Nov 4, 2026
GitHub ↗★ 19.7K⑂ 1.3K
Language Models

raiyanyahya/how-to-train-your-gpt

Build a modern LLM from scratch. Every line commented. Explained like we are five.

🧠 Natural Language Processing
Jupyter NotebookMITupdated Oct 26, 2026
GitHub ↗★ 4.2K⑂ 505
Language Models

parthsarthi03/raptor

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

PythonMITupdated Sep 3, 2024
GitHub ↗★ 1.8K⑂ 236
Language Models

RWKV/rwkv.cpp

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

C++MITupdated Mar 23, 2025
GitHub ↗★ 1.6K⑂ 131
Language Models

NVIDIA/kvpress🔥 active

LLM KV cache compression made easy

PythonApache-2.0updated Nov 9, 2026
GitHub ↗★ 1.2K⑂ 196

Data from GitHub · snapshot Nov 9, 2026