LLM inference in C/C++

A high-throughput and memory-efficient inference and serving engine for LLMs

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

[NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning

collection of benchmarks to measure basic GPU capabilities

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Train transformer language models with reinforcement learning.

A tool for bandwidth measurements on NVIDIA GPUs.

QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning

Fast Hadamard transform in CUDA, with a PyTorch interface

verl: Volcano Engine Reinforcement Learning for LLMs

SGLang is a fast serving framework for large language models and vision language models.

📒 [MKDocs & PDF Version] The C++ Core Guidelines are a set of tried-and-true guidelines, rules, and best practices about coding in C++

Clone a Spotify playlist to YouTube Music

Unify Efficient Fine-Tuning of 100+ LLMs

NVMain - An Architectural Level Main Memory Simulator for Emerging Non-Volatile Memories

Meditron is a suite of open-source medical Large Language Models (LLMs).