Stars
Long context evaluation for large language models
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!
Python library for accurately querying username and email usage on online platforms
OpenAI-Compatible RESTful APIs for Amazon Bedrock
CoreNet: A library for training deep neural networks
Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
Arena-Hard-Auto: An automatic LLM benchmark.
Python bindings for FFmpeg - with complex filtering support
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Accelerating the development of large multimodal models (LMMs) with lmms-eval
Making large AI models cheaper, faster and more accessible
A unified evaluation framework for large language models
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
An extremely fast Python package and project manager, written in Rust.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
SGLang is a fast serving framework for large language models and vision language models.
Python 3.8+ toolbox for submitting jobs to Slurm
pdb++, a drop-in replacement for pdb (the Python debugger)
✨✨Latest Advances on Multimodal Large Language Models
VizTracer is a low-overhead logging/debugging/profiling tool that can trace and visualize your python code execution.
A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
HIP: C++ Heterogeneous-Compute Interface for Portability