facebookresearch / xformersLinks
Hackable and optimized Transformers building blocks, supporting a composable construction.
β9,866Updated last week
Alternatives and similar repositories for xformers
Users that are interested in xformers are comparing it to the libraries listed below
Sorting:
- π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (iβ¦β9,055Updated this week
- Accessible large language models via k-bit quantization for PyTorch.β7,490Updated last week
- Fast and memory-efficient exact attentionβ18,997Updated this week
- Transformer related optimization, including BERT, GPTβ6,274Updated last year
- Using Low-rank adaptation to quickly fine-tune diffusion models.β7,413Updated last year
- An open source implementation of CLIP.β12,398Updated 2 weeks ago
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"β12,544Updated 8 months ago
- Simple, safe way to store and distribute tensorsβ3,403Updated last week
- π€ Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.β30,384Updated this week
- Ongoing research training transformer models at scaleβ13,219Updated this week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (Nβ¦β4,670Updated last week
- Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"β7,724Updated last year
- High-Resolution Image Synthesis with Latent Diffusion Modelsβ13,204Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMsβ10,617Updated last year
- π€ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.β19,350Updated this week
- Foundation Architecture for (M)LLMsβ3,099Updated last year
- π Accelerate inference and training of π€ Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimizationβ¦β3,023Updated this week
- Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.β4,125Updated this week
- PyTorch extensions for high performance and large scale training.β3,361Updated 3 months ago
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)β¦β13,903Updated this week
- A concise but complete full-attention transformer with a set of promising experimental features from various papersβ5,513Updated last week
- Train transformer language models with reinforcement learning.β15,174Updated this week
- PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationβ5,436Updated last year
- Official repo for consistency models.β6,393Updated last year
- β2,863Updated 2 months ago
- π¦ Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorchβ2,153Updated 8 months ago
- Karras et al. (2022) diffusion models for PyTorchβ2,495Updated 7 months ago
- Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.β3,078Updated 3 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.β4,922Updated 4 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blaβ¦β2,645Updated this week