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.
☆4,701Updated last week
Alternatives and similar repositories for AITemplate
Users that are interested in AITemplate are comparing it to the libraries listed below
Sorting:
- Transformer related optimization, including BERT, GPT☆6,384Updated last year
- 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…☆1,586Updated last year
- Training and serving large-scale neural networks with auto parallelization.☆3,173Updated 2 years ago
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,912Updated this week
- PyTorch extensions for high performance and large scale training.☆3,393Updated 8 months ago
- Foundation Architecture for (M)LLMs☆3,133Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆7,912Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,071Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,092Updated last week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,090Updated 6 months ago
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,570Updated last week
- Repo for external large-scale work☆6,542Updated last year
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,260Updated last week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,291Updated 2 weeks ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,928Updated this week
- Development repository for the Triton language and compiler☆18,178Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,380Updated last year
- Simple, safe way to store and distribute tensors☆3,593Updated last week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,854Updated last week
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,645Updated 2 months ago
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,690Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,361Updated last year
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,173Updated last year
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,461Updated last week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,245Updated last year
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,544Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,631Updated this week
- The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.☆1,735Updated this week
- Sparsity-aware deep learning inference runtime for CPUs☆3,159Updated 7 months ago
- LightSeq: A High Performance Library for Sequence Processing and Generation☆3,304Updated 2 years ago