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.
☆4,630Updated 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☆6,147Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆6,972Updated 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…☆1,566Updated last year
- Training and serving large-scale neural networks with auto parallelization.☆3,129Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,435Updated last week
- PyTorch extensions for high performance and large scale training.☆3,309Updated last week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,673Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,009Updated last month
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,135Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,393Updated this week
- Development repository for the Triton language and compiler☆15,447Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,042Updated last year
- Running large language models on a single GPU for throughput-oriented scenarios.☆9,311Updated 6 months ago
- Fast and memory-efficient exact attention☆17,192Updated last week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆2,874Updated last week
- 4 bits quantization of LLaMA using GPTQ☆3,049Updated 9 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,099Updated last year
- Simple, safe way to store and distribute tensors☆3,255Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,387Updated last week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,053Updated 8 months ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,742Updated this week
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,637Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,984Updated 3 weeks ago
- Foundation Architecture for (M)LLMs☆3,073Updated last year
- Tile primitives for speedy kernels☆2,325Updated this week
- Tensor library for machine learning☆12,445Updated this week
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆2,475Updated 8 months ago
- A collection of libraries to optimise AI model performances☆8,370Updated 9 months ago
- Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)☆2,627Updated 2 years ago
- CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.☆2,494Updated this week