Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.

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

Centiman: Elastic, High Performance Optimistic Concurrency Control by Watermarking. SoCC'2015

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Minimal reproduction of DeepSeek R1-Zero

Fix X/Twitter and Bluesky embeds! Use multiple images, videos, polls, translations and more on Discord, Telegram and others

Papermark is the open-source DocSend alternative with built-in analytics and custom domains.

The Rust OpenTelemetry implementation

Hackable and optimized Transformers building blocks, supporting a composable construction.

Sort-friendly URI Reordering Transform (SURT) python module

Index Common Crawl archives in tabular format

Photo Sharing. For Everyone.

A fast PostgreSQL Database Client Library for Python/asyncio.

A command-line tool for using CommonCrawl Index API at http://index.commoncrawl.org/

Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

Accessible large language models via k-bit quantization for PyTorch.

An example project for running Playwright on AWS Lambda using the newly released features of using custom container images as Lambda functions.

🌉 A bridge between decentralized social networks

Your self-hosted, globally interconnected microblogging community

Retrieval with Learned Similarities (http://arxiv.org/abs/2407.15462, WWW'25 Oral)

Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).