FlagOpen / FlagGemsLinks
FlagGems is an operator library for large language models implemented in the Triton Language.
☆551Updated this week
Alternatives and similar repositories for FlagGems
Users that are interested in FlagGems are comparing it to the libraries listed below
Sorting:
- Distributed Triton for Parallel Systems☆775Updated last week
- A collection of memory efficient attention operators implemented in the Triton language.☆271Updated last year
- Puzzles for learning Triton, play it with minimal environment configuration!☆334Updated 6 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆360Updated 8 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆370Updated 3 weeks ago
- Development repository for the Triton-Linalg conversion☆189Updated 3 months ago
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆415Updated 8 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆605Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆384Updated this week
- learning how CUDA works☆264Updated 3 months ago
- Yinghan's Code Sample☆328Updated 2 years ago
- how to learn PyTorch and OneFlow☆433Updated last year
- Examples of CUDA implementations by Cutlass CuTe☆188Updated 4 months ago
- Materials for learning SGLang☆426Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆690Updated 3 months ago
- ☆208Updated 10 months ago
- Shared Middle-Layer for Triton Compilation☆251Updated this week
- Zero Bubble Pipeline Parallelism☆396Updated 3 weeks ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆619Updated last month
- A model compilation solution for various hardware☆437Updated this week
- Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.☆353Updated 5 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆473Updated last year
- GLake: optimizing GPU memory management and IO transmission.☆463Updated 2 months ago
- ☆139Updated last year
- A low-latency & high-throughput serving engine for LLMs☆370Updated this week
- FlagScale is a large model toolkit based on open-sourced projects.☆281Updated this week
- A simple high performance CUDA GEMM implementation.☆374Updated last year
- Step-by-step optimization of CUDA SGEMM☆333Updated 3 years ago
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆476Updated last week
- 📚FFPA(Split-D): Extend FlashAttention with Split-D for large headdim, O(1) GPU SRAM complexity, 1.8x~3x↑🎉 faster than SDPA EA.☆184Updated 3 weeks ago