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.
☆4,691Updated 2 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☆6,344Updated last year
- Training and serving large-scale neural networks with auto parallelization.☆3,162Updated last year
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, …☆2,520Updated this week
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,650Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,883Updated last week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,164Updated last week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,066Updated last year
- PyTorch extensions for high performance and large scale training.☆3,385Updated 6 months ago
- Foundation Architecture for (M)LLMs☆3,119Updated last year
- Simple, safe way to store and distribute tensors☆3,501Updated last week
- Sparsity-aware deep learning inference runtime for CPUs☆3,160Updated 5 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,083Updated last week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,073Updated 4 months ago
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,598Updated 5 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆7,737Updated last week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,878Updated this week
- Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀☆1,688Updated last year
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,492Updated this week
- Development repository for the Triton language and compiler☆17,529Updated this week
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,373Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,843Updated this week
- High-efficiency floating-point neural network inference operators for mobile, server, and Web☆2,158Updated this week
- The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.☆1,674Updated this week
- 4 bits quantization of LLaMA using GPTQ☆3,076Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,217Updated last year
- Library for reading and writing large multi-dimensional arrays.☆1,464Updated this week
- A retargetable MLIR-based machine learning compiler and runtime toolkit.☆3,450Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,165Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,332Updated 3 months ago