microsoft / arkLinks
A GPU-driven system framework for scalable AI applications
☆122Updated 10 months ago
Alternatives and similar repositories for ark
Users that are interested in ark are comparing it to the libraries listed below
Sorting:
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆442Updated this week
- An experimental parallel training platform☆56Updated last year
- Microsoft Collective Communication Library☆66Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆64Updated 2 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆407Updated last month
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆70Updated 7 months ago
- ☆25Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆65Updated last year
- ☆96Updated last year
- An experimental CPU backend for Triton (https//github.com/openai/triton)☆47Updated 3 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆190Updated 10 months ago
- A lightweight design for computation-communication overlap.☆194Updated 2 months ago
- Open ABI and FFI for Machine Learning Systems☆236Updated this week
- NCCL Profiling Kit☆149Updated last year
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆66Updated last month
- A language and compiler for irregular tensor programs.☆152Updated last year
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆282Updated 3 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆104Updated 5 months ago
- ☆83Updated 3 years ago
- ☆67Updated 6 months ago
- High performance Transformer implementation in C++.☆143Updated 10 months ago
- ☆26Updated 9 months ago
- Thunder Research Group's Collective Communication Library☆43Updated 5 months ago
- An extension library of WMMA API (Tensor Core API)☆109Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆135Updated 7 months ago
- ☆16Updated last year
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆118Updated 6 months ago
- PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for…☆154Updated this week
- PTX-EMU is a simple emulator for CUDA program.☆38Updated 7 months ago
- Intel® Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Note…☆63Updated 5 months ago