kyegomez / FlashAttention20
Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels
☆102Updated last year
Alternatives and similar repositories for FlashAttention20:
Users that are interested in FlashAttention20 are comparing it to the libraries listed below
- ☆147Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆174Updated 10 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆127Updated 2 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆279Updated 2 months ago
- The official implementation of the EMNLP 2023 paper LLM-FP4☆195Updated last year
- Triton implementation of Flash Attention2.0☆32Updated last year
- Implementation of FlashAttention in PyTorch☆143Updated 3 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆304Updated 9 months ago
- This repository contains integer operators on GPUs for PyTorch.☆202Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆184Updated this week
- Low-bit optimizers for PyTorch☆128Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆109Updated 11 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆376Updated 4 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆248Updated 5 months ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆280Updated last month
- ☆48Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆81Updated 5 months ago
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆68Updated 11 months ago
- ☆157Updated last year
- Reorder-based post-training quantization for large language model☆187Updated last year
- PB-LLM: Partially Binarized Large Language Models☆151Updated last year
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆35Updated 10 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆97Updated 6 months ago
- The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆123Updated 4 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆288Updated 3 months ago
- ☆122Updated 2 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆158Updated 10 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆159Updated 9 months ago
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆168Updated 3 weeks ago
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆121Updated 3 months ago