Dao-AILab / flash-attentionLinks
Fast and memory-efficient exact attention
☆21,196Updated 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:
- Accessible large language models via k-bit quantization for PyTorch.☆7,845Updated last week
- Train transformer language models with reinforcement learning.☆16,722Updated this week
- Ongoing research training transformer models at scale☆14,602Updated last week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆20,307Updated this week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,398Updated this week
- Transformer related optimization, including BERT, GPT☆6,370Updated last year
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,201Updated last week
- Development repository for the Triton language and compiler☆17,861Updated last week
- A framework for few-shot evaluation of language models.☆10,976Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆13,093Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆65,845Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆12,433Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆21,569Updated last week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,407Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,795Updated last week
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,786Updated last year
- Mamba SSM architecture☆16,778Updated last month
- An open source implementation of CLIP.☆13,150Updated last month
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling…☆8,625Updated this week
- Large Language Model Text Generation Inference☆10,709Updated last week
- Tools for merging pretrained large language models.☆6,611Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,169Updated 4 months ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆17,582Updated this week
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆14,233Updated this week
- Go ahead and axolotl questions☆10,974Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,389Updated 5 months ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (…☆11,695Updated last week
- PyTorch native post-training library☆5,619Updated last week
- LAVIS - A One-stop Library for Language-Vision Intelligence☆11,073Updated last year
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆24,188Updated last year