xLLM-AI/xllm🔥 active
▲ +4 ★ this week
A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
PyTorch library for cost-effective, fast and easy serving of MoE models.
$ git clone https://github.com/EfficientMoE/MoE-Infinity.git▲ +4 ★ this week
A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression
<밑바닥부터 만들면서 공부하는 LLM>(길벗, 2025)의 코드 저장소
Data from GitHub · snapshot Nov 13, 2026