Stars
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
A best practice for deep learning project template architecture.
The loss landscape of Large Language Models resemble basin!
bg6cq / speedtest
Forked from librespeed/speedtestLightweight HTML5 Speedtest
[ACL2025 Main] Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
MCPToolBench++ MCP Model Context Protocol Tool Use Benchmark on AI Agent and Model Tool Use Ability
Code Repo for EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
Lab Materials for MIT 6.S191: Introduction to Deep Learning
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
Model Context Protocol Servers
[ECCV'24] Online Vectorized HD Map Construction using Geometry
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Official implementation of MASS: Multi-Agent Simulation Scaling for Portfolio Construction
Implementation of "Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines"
An extremely fast Python package and project manager, written in Rust.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
Google Research