Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

The best OSS video generation models

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

A bibliography and survey of the papers surrounding o1

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"

A sparse attention kernel supporting mix sparse patterns

FlashInfer: Kernel Library for LLM Serving

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Run PyTorch LLMs locally on servers, desktop and mobile

Helpful tools and examples for working with flex-attention

This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

The Memory layer for your AI apps

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Pipeline Parallelism for PyTorch

open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality

The official Meta Llama 3 GitHub site

LLM training in simple, raw C/CUDA

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-sim…

[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challen…

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

🙌 OpenHands: Code Less, Make More

Code examples and resources for DBRX, a large language model developed by Databricks