Stars
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
A framework for few-shot evaluation of language models.
tenstorrent / vllm
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
TT-Studio : An all-in-one platform to deploy and manage AI models optimized for Tenstorrent hardware with dedicated front-end demo applications.
[Deprecated] ⭐️ TT-NN Compiler for PyTorch 2 ⭐️ Enables running PyTorch models on Tenstorrent hardware using eager or compile path
The little ASGI framework that shines. 🌟
The fastest way to create an HTML app
100+ AI Agent & RAG apps you can actually run — clone, customize, ship.
High-Performance server for NATS.io, the cloud and edge native messaging system.
🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.
Tenstorrent console based hardware information program
Repository of model demos using TT-Buda
Buda Compiler Backend for Tenstorrent devices
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Fast and memory-efficient exact attention
Structured state space sequence models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
TensorFlow code and pre-trained models for BERT