bytedance / flux
A fast communication-overlapping library for tensor parallelism on GPUs.
☆217Updated last week
Related projects ⓘ
Alternatives and complementary repositories for flux
- Dynamic Memory Management for Serving LLMs without PagedAttention☆222Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆287Updated last month
- ☆162Updated 3 months ago
- ☆79Updated 2 months ago
- A low-latency & high-throughput serving engine for LLMs☆231Updated last month
- A collection of memory efficient attention operators implemented in the Triton language.☆215Updated 5 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆194Updated 4 months ago
- Zero Bubble Pipeline Parallelism☆279Updated this week
- ☆78Updated 8 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆166Updated this week
- TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.☆148Updated this week
- High performance Transformer implementation in C++.☆78Updated last month
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆296Updated 2 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆75Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆196Updated last week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆246Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆87Updated 3 months ago
- FlagGems is an operator library for large language models implemented in Triton Language.☆328Updated this week
- ☆130Updated 3 months ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆142Updated 2 years ago
- ☆136Updated this week
- nnScaler: Compiling DNN models for Parallel Training☆62Updated 2 weeks ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆46Updated 3 months ago
- paper and its code for AI System☆210Updated 2 months ago
- Shared Middle-Layer for Triton Compilation☆185Updated this week
- ☆121Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆277Updated 4 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆177Updated last year
- ☆72Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆348Updated 2 months ago