Pinned Loading

1. NVIDIA/TensorRT-LLM NVIDIA/TensorRT-LLM Public

   TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…

   C++ 11.5k 1.7k

2. huggingface/transformers huggingface/transformers Public

   🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

   Python 149k 30.2k

3. NVIDIA/TensorRT-Model-Optimizer NVIDIA/TensorRT-Model-Optimizer Public

   A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment…

   Python 1.2k 123

4. huggingface/diffusers huggingface/diffusers Public

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

   Python 30.5k 6.3k

5. huggingface/accelerate huggingface/accelerate Public

   🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

   Python 9.1k 1.2k