bytedance / flux
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
☆787Updated this week
Alternatives and similar repositories for flux:
Users that are interested in flux are comparing it to the libraries listed below
- A PyTorch Native LLM Training Framework☆759Updated 2 months ago
- FlashInfer: Kernel Library for LLM Serving☆2,439Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆773Updated 6 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆782Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆507Updated 7 months ago
- Materials for learning SGLang☆345Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆452Updated this week
- Zero Bubble Pipeline Parallelism☆373Updated 3 weeks ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆326Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆611Updated 2 weeks ago
- Redis for LLMs☆624Updated this week
- Efficient and easy multi-instance LLM serving☆339Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆670Updated 2 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆423Updated 6 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆253Updated this week
- FlagGems is an operator library for large language models implemented in Triton Language.☆457Updated this week
- GLake: optimizing GPU memory management and IO transmission.☆445Updated 3 months ago
- Microsoft Automatic Mixed Precision Library☆581Updated 5 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆471Updated last year
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆557Updated last month
- Ring attention implementation with flash attention☆714Updated last month
- A low-latency & high-throughput serving engine for LLMs☆327Updated last month
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆775Updated 6 months ago
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆436Updated last week
- Efficient LLM Inference over Long Sequences☆365Updated last month
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆771Updated this week
- 📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉☆199Updated this week
- Expert Parallelism Load Balancer☆1,099Updated this week
- Serverless LLM Serving for Everyone.☆441Updated this week
- flash attention tutorial written in python, triton, cuda, cutlass☆302Updated 2 months ago