The fastest way to create an HTML app

Blazingly fast LLM inference.

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Agentic components of the Llama Stack APIs

A high-throughput and memory-efficient inference and serving engine for LLMs

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip

SGLang is a fast serving framework for large language models and vision language models.

Large-scale LLM inference engine

LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

🙌 OpenHands: Code Less, Make More

Must-read Papers on LLM Agents.

This document helps demystify the PhD admission process in Computer Science in US universities.

Alpaca dataset from Stanford, cleaned and curated

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Python logging made (stupidly) simple

A powerful, lightweight theme for Hugo built with Tailwind CSS.

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

The LLM Evaluation Framework

Fast and memory-efficient exact attention

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

A Unified Toolkit for Deep Learning Based Document Image Analysis

Build better UIs faster.

Python bindings for llama.cpp

LLM inference in C/C++

LLM Finetuning with peft

This repo includes ChatGPT prompt curation to use ChatGPT better.

Train transformer language models with reinforcement learning.

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Human Video Generation Paper List