AI-Driven Exploration in the Space of Code
SQL-Driven RAG Engine
A Next-Generation Training Engine Built for Ultra-Large MoE Models
A lightweight vLLM implementation built from scratch
Tensor search for humans
local-first semantic code search engine
Big Model Application Development Practice 1
A high-throughput and memory-efficient inference and serving engine
LightLLM is a Python-based LLM (Large Language Model) inference
High-performance inference framework for large language models
Request recommended movies, TV shows and anime to Jellyseer/Overseer
Build multimodal language agents for fast prototype and production
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding
Retrieval Augmented Generation (RAG) framework
Official Implementation of "Graph of Thoughts
AI-powered CLI git wrapper, boilerplate code generator, chat history
Experimental search engine for conversational AI such as parl.ai