A fast communication-overlapping library for tensor/expert parallelism on GPUs.
☆1,284Aug 28, 2025Updated 7 months ago
Alternatives and similar repositories for flux
Users that are interested in flux are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Distributed Compiler based on Triton for Parallel Systems☆1,403Updated this week
- A lightweight design for computation-communication overlap.☆226Jan 20, 2026Updated 2 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,372Updated this week
- Perplexity GPU Kernels☆565Nov 7, 2025Updated 5 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆498Updated this week
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A throughput-oriented high-performance serving framework for LLMs☆952Mar 29, 2026Updated 2 weeks ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,071Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆474May 30, 2025Updated 10 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆422Mar 5, 2026Updated last month
- Tile primitives for speedy kernels☆3,312Apr 8, 2026Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,269Updated this week
- DeepEP: an efficient expert-parallel communication library☆9,105Updated this week
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆1,004Mar 3, 2026Updated last month
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,051Sep 4, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆261Jul 11, 2024Updated last year
- Ring attention implementation with flash attention☆1,006Sep 10, 2025Updated 7 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,184Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,564Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆664Jan 15, 2026Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆320Aug 22, 2025Updated 7 months ago
- Zero Bubble Pipeline Parallelism☆452May 7, 2025Updated 11 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆765Apr 8, 2026Updated last week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,478Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,319Mar 22, 2026Updated 3 weeks ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,590Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆970Updated this week
- ☆166Dec 27, 2024Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆826Mar 6, 2025Updated last year
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,937Jan 14, 2026Updated 3 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆758Aug 6, 2025Updated 8 months ago
- ☆65Apr 26, 2025Updated 11 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆801Apr 6, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Efficient and easy multi-instance LLM serving☆543Mar 12, 2026Updated last month
- Analyze computation-communication overlap in V3/R1.☆1,149Mar 21, 2025Updated last year
- ☆359Jan 28, 2026Updated 2 months ago
- GLake: optimizing GPU memory management and IO transmission.☆501Mar 24, 2025Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,997Updated this week
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆193Jan 28, 2025Updated last year
- A model compilation solution for various hardware☆469Aug 20, 2025Updated 7 months ago