Tile primitives for speedy kernels

Efficient Triton Kernels for LLM Training

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

A generative world for general-purpose robotics & embodied AI learning.

Efficient and easy multi-instance LLM serving

Large-scale LLM inference engine

📖A curated list of Awesome LLM/VLM Inference Papers with codes, such as FlashAttention, PagedAttention, Parallelism, etc. 🎉🎉

Virtual Machine for the Web

CUDA Python: Performance meets Productivity

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

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

[CVPR24] CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation

Puzzles for learning Triton, play it with minimal environment configuration!

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

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

An Open-Ended Embodied Agent with Large Language Models

A modern client-side schematic mod for Minecraft

Inference script for Oasis 500M

A large-scale simulation framework for LLM inference

Create Minecraft bots with a powerful, stable, and high level JavaScript API.

Rust bindings for the C++ api of PyTorch.

pyright fork with various type checking improvements, improved vscode support and pylance features built into the language server

Material for gpu-mode lectures

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

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

The best OSS video generation models