facebookincubator / AITemplate
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.
☆4,585Updated last month
Alternatives and similar repositories for AITemplate:
Users that are interested in AITemplate are comparing it to the libraries listed below
- Transformer related optimization, including BERT, GPT☆5,981Updated 9 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆6,522Updated this week
- 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…☆1,549Updated 11 months ago
- Fast and memory-efficient exact attention☆15,064Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆8,910Updated this week
- Simple, safe way to store and distribute tensors☆3,010Updated last week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,647Updated this week
- Foundation Architecture for (M)LLMs☆3,038Updated 9 months ago
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆2,847Updated this week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,667Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,086Updated this week
- Training and serving large-scale neural networks with auto parallelization.☆3,093Updated last year
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,178Updated this week
- PyTorch extensions for high performance and large scale training.☆3,232Updated this week
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,422Updated last month
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,016Updated 9 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,942Updated last month
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,298Updated this week
- Sparsity-aware deep learning inference runtime for CPUs☆3,077Updated 5 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,669Updated last week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,998Updated 9 months ago
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,749Updated 6 months ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,152Updated 3 months ago
- Development repository for the Triton language and compiler☆14,042Updated this week
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.☆2,426Updated last month
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,616Updated last month
- Tensor library for machine learning☆11,541Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,021Updated 4 months ago