Accelerating-Cross-Encoder-Inference

基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答

? A Human-in-the-Loop workflow for creating HD images from text

High-efficiency floating-point neural network inference operators for mobile, server, and Web

:dart: Task-oriented embedding tuning for BERT, CLIP, etc.

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

? DiscovAI-Search: An AI-powered search engine for AI tools and custom data. Built with Next.js, OpenAI, Supabase, and more. Features vector-based search, Redis caching, and LLM-powered responses.

This project provides a powerful web scraping tool that fetches search results and converts them into Markdown format using FastAPI, SearXNG, and Browserless. It includes the capability to use proxies for web scraping and handles HTML content conversion to Markdown efficiently.

[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration

RAG on codebases using treesitter and LanceDB