Unofficial Node.js API client for the Caret HTTP API

OAuth Solution for AI Agents

Turn any computer or edge device into a command center for your computer vision projects.

An open-source AI agent that brings the power of Gemini directly into your terminal.

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

Inference Llama 2 in one file of pure C

LLM training code for Databricks foundation models

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

Implementation of Flash Attention in Jax

Making large AI models cheaper, faster and more accessible

The code of Zero To Production In Rust for exercise

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

A latent text-to-image diffusion model

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

Everything you want to know about Google Cloud TPU

DALL·E Mini - Generate images from a text prompt

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

Tool for Multi-stage Review Process

PyTorch Implementation of the Paper "Efficient Training of Retrieval Models using Negative Cache"

Training and serving large-scale neural networks with auto parallelization.

Go binding to TensorRT C API to do inference with pre-trained model in Go

common in-memory tensor structure