bytedance / fluxLinks
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
☆1,072Updated this week
Alternatives and similar repositories for flux
Users that are interested in flux are comparing it to the libraries listed below
Sorting:
- Distributed Compiler based on Triton for Parallel Systems☆1,031Updated last week
- A PyTorch Native LLM Training Framework☆861Updated last month
- Materials for learning SGLang☆530Updated last month
- Perplexity GPU Kernels☆435Updated 2 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,530Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆669Updated 4 months ago
- A throughput-oriented high-performance serving framework for LLMs☆872Updated last week
- Efficient and easy multi-instance LLM serving☆468Updated this week
- GLake: optimizing GPU memory management and IO transmission.☆473Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆407Updated 2 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆648Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆838Updated 3 weeks ago
- ☆483Updated 2 weeks ago
- Zero Bubble Pipeline Parallelism☆418Updated 3 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆346Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆313Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆735Updated 5 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆461Updated 8 months ago
- NVIDIA Inference Xfer Library (NIXL)☆557Updated this week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆528Updated 11 months ago
- Expert Parallelism Load Balancer☆1,250Updated 4 months ago
- Analyze computation-communication overlap in V3/R1.☆1,090Updated 5 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆549Updated last month
- KV cache store for distributed LLM inference☆311Updated 2 months ago
- FlashInfer: Kernel Library for LLM Serving☆3,571Updated this week
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆1,688Updated this week
- A low-latency & high-throughput serving engine for LLMs☆405Updated 2 months ago
- ☆279Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆880Updated 11 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆404Updated 3 months ago