Dao-AILab / flash-attentionLinks
Fast and memory-efficient exact attention
β18,340Updated 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.β7,230Updated this week
- π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (iβ¦β8,941Updated last week
- π€ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.β19,028Updated last week
- Hackable and optimized Transformers building blocks, supporting a composable construction.β9,729Updated this week
- Ongoing research training transformer models at scaleβ12,910Updated this week
- Train transformer language models with reinforcement learning.β14,607Updated this week
- SGLang is a fast serving framework for large language models and vision language models.β16,097Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"β12,251Updated 7 months ago
- Transformer related optimization, including BERT, GPTβ6,248Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMsβ52,204Updated this week
- TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizatiβ¦β11,003Updated last week
- QLoRA: Efficient Finetuning of Quantized LLMsβ10,561Updated last year
- Development repository for the Triton language and compilerβ16,198Updated this week
- A framework for few-shot evaluation of language models.β9,588Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.β6,705Updated last week
- Large Language Model Text Generation Inferenceβ10,334Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationβ3,154Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.β39,392Updated this week
- An open source implementation of CLIP.β12,176Updated last month
- verl: Volcano Engine Reinforcement Learning for LLMsβ11,168Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asyβ¦β7,344Updated last week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.β4,897Updated 3 months ago
- Mamba SSM architectureβ15,378Updated 3 weeks ago
- Modeling, training, eval, and inference code for OLMoβ5,778Updated this week
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalitiesβ21,552Updated 2 weeks ago
- Inference Llama 2 in one file of pure Cβ18,566Updated 11 months ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parametersβ5,884Updated last year
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinksβ6,933Updated last year
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.β23,029Updated 11 months ago
- Example models using DeepSpeedβ6,576Updated last week