FlagOpen / FlagAttentionLinks
A collection of memory efficient attention operators implemented in the Triton language.
☆278Updated last year
Alternatives and similar repositories for FlagAttention
Users that are interested in FlagAttention are comparing it to the libraries listed below
Sorting:
- PyTorch bindings for CUTLASS grouped GEMM.☆137Updated last month
- flash attention tutorial written in python, triton, cuda, cutlass☆408Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆110Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆411Updated last week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆207Updated this week
- ☆229Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆261Updated last month
- This repository contains integer operators on GPUs for PyTorch.☆213Updated last year
- ☆98Updated 11 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆655Updated this week
- ☆146Updated 5 months ago
- Applied AI experiments and examples for PyTorch☆291Updated last week
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆211Updated 3 weeks ago
- Zero Bubble Pipeline Parallelism☆421Updated 3 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆325Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆408Updated 2 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆104Updated 4 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆374Updated 11 months ago
- Cataloging released Triton kernels.☆252Updated 7 months ago
- Pipeline Parallelism Emulation and Visualization☆63Updated 2 months ago
- ☆332Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 6 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆64Updated this week
- Implement Flash Attention using Cute.☆95Updated 8 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆138Updated last week
- nnScaler: Compiling DNN models for Parallel Training☆115Updated last week
- Examples of CUDA implementations by Cutlass CuTe☆222Updated last month
- Fast Hadamard transform in CUDA, with a PyTorch interface☆224Updated last year