Lists (1)
Starred repositories
HMLL - High-Performance Model Loading Library for Efficient AI Model I/O
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
A simple, performant and scalable Jax LLM!
A pytorch quantization backend for optimum
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Transformer related optimization, including BERT, GPT
The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
Backward compatible ML compute opset inspired by HLO/MHLO
Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
State-of-the-Art Text Embeddings
Blazing fast training of 🤗 Transformers on Graphcore IPUs
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Hydra is a framework for elegantly configuring complex applications
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
Dapr user documentation, used to build docs.dapr.io
[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl
Simple Python client for the Hugging Face Inference API
The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Cross-platform CLI and Python drivers for AIO liquid coolers and other devices
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.