Universal LLM Deployment Engine with ML Compilation

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…

Sky-T1: Train your own O1 preview model within $450

procedural reasoning datasets

Convert any PDF into a podcast episode!

Minimalist LLM Framework in 100 Lines. Enable LLMs to Program Themselves.

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

A fast and efficient type assistant for Python, including tensor shape inference

[NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank

FastVideo is a lightweight framework for accelerating large video diffusion models.

The Multi-Faceted Optimizer for GenAI Workflows

Let your Claude able to think

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Teaching materials for the applied machine learning course at Cornell Tech (online edition)

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

Low-bit LLM inference on CPU with lookup table

STREAM benchmark

A library for advanced large language model reasoning

Entropy Based Sampling and Parallel CoT Decoding

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

A bibliography and survey of the papers surrounding o1

[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Composable building blocks to build Llama Apps

A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI