Lists (13)
Stars
SGLang is a high-performance serving framework for large language models and multimodal models.
A fast, cross-platform build tool inspired by Make, designed for modern workflows.
Tile primitives for speedy kernels
This repository contains the Hugging Face Agents Course.
Quack is a free and open-source chat application designed for private use. Although it doesn't have any unique features, it combines the best features from other communicators. Quack prioritizes pr…
A Lightweight Library for AI Observability
Generalist and Lightweight Model for Relation Extraction (Extract any relationship types from text)
Experimental wasm32-unknown-wasi runtime for Python code execution
A flexible library for benchmarking LLMs on HF Inference Endpoints
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
A feature-rich command-line audio/video downloader
Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget (ACL 2024)
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Bringing BERT into modernity via both architecture changes and scaling
🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
Efficient Triton Kernels for LLM Training
Solution of Kaggle competition: LMSYS - Chatbot Arena Human Preference Predictions
The fastest way to create an HTML app
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
AMD related optimizations for transformer models
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy
No-code in the front, Python in the back. An open-source framework for creating data apps.