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.
☆4,695Updated last month
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☆6,355Updated 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…☆1,585Updated last year
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,714Updated last week
- Training and serving large-scale neural networks with auto parallelization.☆3,167Updated last year
- Simple, safe way to store and distribute tensors☆3,528Updated 2 weeks ago
- PyTorch extensions for high performance and large scale training.☆3,386Updated 7 months ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,894Updated last week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,192Updated 2 weeks ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,079Updated 5 months ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,067Updated last year
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,610Updated 2 weeks ago
- Sparsity-aware deep learning inference runtime for CPUs☆3,161Updated 6 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆2,954Updated last week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,131Updated 2 weeks ago
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,537Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆7,790Updated last week
- Foundation Architecture for (M)LLMs☆3,121Updated last year
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,688Updated last year
- Development repository for the Triton language and compiler☆17,730Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,379Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,846Updated this week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,329Updated this week
- The Triton Inference Server provides an optimized cloud and edge inferencing solution.☆10,084Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,543Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,167Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,226Updated last year
- Repo for external large-scale work☆6,548Updated last year
- Tile primitives for speedy kernels☆2,955Updated this week
- 4 bits quantization of LLaMA using GPTQ☆3,081Updated last year
- A collection of libraries to optimise AI model performances☆8,363Updated last year