Change the repository type filter
All
Repositories list
643 repositories
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
- A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
- BioNeMo Framework: For building and adapting AI models in drug discovery at scale
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
- CUDA Core Compute Libraries
- Ongoing research training transformer models at scale
- C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows
- AIStore: scalable storage for AI applications
- Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
- GPU accelerated decision optimization
- A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
- Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.