facebookincubator / AITemplateLinks
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
☆4,694Updated 3 weeks ago
Alternatives and similar repositories for AITemplate
Users that are interested in AITemplate are comparing it to the libraries listed below
Sorting:
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,585Updated last year
- Transformer related optimization, including BERT, GPT☆6,378Updated last year
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,880Updated this week
- PyTorch extensions for high performance and large scale training.☆3,393Updated 8 months ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,071Updated last year
- Training and serving large-scale neural networks with auto parallelization.☆3,174Updated 2 years ago
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,565Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,055Updated last week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,086Updated 6 months ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,917Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,257Updated this week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,237Updated 3 weeks ago
- Foundation Architecture for (M)LLMs☆3,130Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆7,881Updated this week
- Simple, safe way to store and distribute tensors☆3,581Updated 3 weeks ago
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,630Updated last month
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,689Updated last year
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,427Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,383Updated last year
- Tile primitives for speedy kernels☆3,038Updated this week
- Repo for external large-scale work☆6,547Updated last year
- The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.☆1,715Updated last week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,172Updated last year
- PyTorch native quantization and sparsity for training and inference☆2,617Updated this week
- Enabling PyTorch on XLA Devices (e.g. Google TPU)☆2,737Updated 3 weeks ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,243Updated last year
- Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)☆2,672Updated 2 years ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,854Updated last week
- Sparsity-aware deep learning inference runtime for CPUs☆3,160Updated 7 months ago
- Tensor library for machine learning☆13,812Updated this week