Dao-AILab / flash-attentionLinks
Fast and memory-efficient exact attention
β17,572Updated last week
Alternatives and similar repositories for flash-attention
Users that are interested in flash-attention are comparing it to the libraries listed below
Sorting:
- Accessible large language models via k-bit quantization for PyTorch.β7,064Updated last week
- π€ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.β18,598Updated this week
- Transformer related optimization, including BERT, GPTβ6,173Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.β9,527Updated this week
- π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (iβ¦β8,771Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"β11,977Updated 5 months ago
- Train transformer language models with reinforcement learning.β13,971Updated this week
- SGLang is a fast serving framework for large language models and vision language models.β14,667Updated this week
- Development repository for the Triton language and compilerβ15,687Updated this week
- Ongoing research training transformer models at scaleβ12,428Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMsβ48,531Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMsβ10,446Updated 11 months ago
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizatiβ¦β10,586Updated this week
- Mamba SSM architectureβ14,927Updated this week
- Large Language Model Text Generation Inferenceβ10,155Updated this week
- A framework for few-shot evaluation of language models.β9,069Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.β4,856Updated last month
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.β22,643Updated 9 months ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.β38,566Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.β6,427Updated this week
- PyTorch native post-training libraryβ5,217Updated this week
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalitiesβ21,289Updated 2 months ago
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinksβ6,898Updated 10 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.β5,960Updated last month
- LAVIS - A One-stop Library for Language-Vision Intelligenceβ10,586Updated 6 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabiliβ¦β3,247Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationβ3,029Updated 3 weeks ago
- Tensor library for machine learningβ12,591Updated this week
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)β¦β13,645Updated this week
- An open source implementation of CLIP.β11,810Updated last week