Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

An Aspiring Drop-In Replacement for NumPy at Scale

Code I wrote for my AI & LLM workshops

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

🌈 React for interactive command-line apps

🦄 Record your terminal and generate animated gif images or share a web player

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream d…

Experimental projects related to TensorRT

📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, Flash-Attention, Paged-Attention, Parallelism, etc. 🎉🎉

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

An AI search engine inspired by Perplexity

CUDA checkpoint and restore utility

Checkpoint/Restore tool

The visual editor for React

A framework for evaluating function calls made by LLMs

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Mamba SSM architecture

[ACL 2024 Demo] SeaLLMs - Large Language Models for Southeast Asia

Contrastive Chain-of-Thought Prompting

Evaluate the accuracy of LLM generated outputs

The Triton TensorRT-LLM Backend

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Fast and memory-efficient exact attention

GitHub Action for advanced repository traffic analysis and reporting