tinaxfwu
Follow
Lists (5)
Stars
A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！
🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper
A native PyTorch Library for large model training
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Zero Bubble Pipeline Parallelism
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
An open-source RAG-based tool for chatting with your documents.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
😎 Awesome lists about all kinds of interesting topics
Development repository for the Triton language and compiler
GPU programming related news and material links
Efficient Triton Kernels for LLM Training
An isomorphic Javascript client for Supabase. Query your Supabase database, subscribe to realtime events, upload and download files, browse typescript examples, invoke postgres functions via rpc, i…
The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
A cross platform CLI for Flyte. Written in Golang. Offers an intuitive interface to Flyte https://docs.flyte.org/projects/flytectl/en/latest/
Apache Beam is a unified programming model for Batch and Streaming data processing.
Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.
A Python framework for high performance GPU simulation and graphics
A lightweight library for portable low-level GPU computation using WebGPU.