bytedance / fluxLinks
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
☆1,214Updated 4 months ago
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☆1,303Updated last week
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆912Updated last month
- Disaggregated serving system for Large Language Models (LLMs).☆758Updated 8 months ago
- Perplexity GPU Kernels☆547Updated last month
- Materials for learning SGLang☆709Updated 2 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆597Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆929Updated 2 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆819Updated this week
- Efficient and easy multi-instance LLM serving☆519Updated 4 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆583Updated last week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆972Updated last week
- NVIDIA Inference Xfer Library (NIXL)☆783Updated this week
- GLake: optimizing GPU memory management and IO transmission.☆494Updated 9 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆4,336Updated this week
- Zero Bubble Pipeline Parallelism☆444Updated 7 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆799Updated 9 months ago
- Expert Parallelism Load Balancer☆1,324Updated 9 months ago
- Analyze computation-communication overlap in V3/R1.☆1,129Updated 9 months ago
- ☆518Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆453Updated 7 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆600Updated last year
- ☆336Updated 2 weeks ago
- FlagScale is a large model toolkit based on open-sourced projects.☆430Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆619Updated last week
- A low-latency & high-throughput serving engine for LLMs☆459Updated 2 months ago
- KV cache store for distributed LLM inference☆378Updated last month
- FlashInfer: Kernel Library for LLM Serving☆4,400Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,015Updated 2 weeks ago
- flash attention tutorial written in python, triton, cuda, cutlass☆471Updated 7 months ago
- Ring attention implementation with flash attention☆957Updated 3 months ago