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

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

Official repository for EXAONE 3.5 built by LG AI Research

LOFT: A 1 Million+ Token Long-Context Benchmark

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

Development repository for the Triton language and compiler

InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.

AcadHomepage: A Modern and Responsive Academic Personal Homepage

A framework for few-shot evaluation of language models.

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Numba optimized version of `pypareto`. Sorting chains for pareto frontier extraction

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A Python library that adds Latex functionality to the Texttable package.