Dao-AILab / flash-attentionLinks
Fast and memory-efficient exact attention
☆19,778Updated this week
Alternatives and similar repositories for flash-attention
Users that are interested in flash-attention are comparing it to the libraries listed below
Sorting:
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆9,978Updated last week
- Accessible large language models via k-bit quantization for PyTorch.☆7,627Updated this week
- Transformer related optimization, including BERT, GPT☆6,321Updated last year
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆19,743Updated this week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,180Updated last week
- Train transformer language models with reinforcement learning.☆15,739Updated this week
- Ongoing research training transformer models at scale☆13,728Updated last week
- SGLang is a fast serving framework for large language models and vision language models.☆18,528Updated this week
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆13,997Updated last week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,134Updated last week
- Development repository for the Triton language and compiler☆17,069Updated last week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆12,775Updated 9 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 optimizati…☆11,773Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,679Updated last year
- A framework for few-shot evaluation of language models.☆10,270Updated this week
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆23,663Updated last year
- An open source implementation of CLIP.☆12,702Updated 2 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,282Updated 2 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆59,413Updated this week
- PyTorch native post-training library☆5,517Updated last week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,763Updated last year
- Mamba SSM architecture☆15,994Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,952Updated 5 months ago
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,055Updated last year
- Large Language Model Text Generation Inference☆10,539Updated 3 weeks ago
- Tools for merging pretrained large language models.☆6,337Updated 2 weeks ago
- LAVIS - A One-stop Library for Language-Vision Intelligence☆10,936Updated 10 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,626Updated last week
- High-speed Large Language Model Serving for Local Deployment☆8,347Updated 2 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆13,956Updated last week