microsoft / arkLinks
A GPU-driven system framework for scalable AI applications
☆119Updated 8 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☆427Updated this week
- Microsoft Collective Communication Library☆66Updated 11 months ago
- ☆25Updated last year
- An experimental parallel training platform☆54Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆62Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆63Updated last month
- ☆27Updated 8 months ago
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆65Updated 5 months ago
- RCCL Performance Benchmark Tests☆76Updated 2 weeks ago
- NCCL Profiling Kit☆145Updated last year
- An extension library of WMMA API (Tensor Core API)☆107Updated last year
- TransferBench is a utility capable of benchmarking simultaneous copies between user-specified devices (CPUs/GPUs)☆50Updated last week
- A memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.☆26Updated last year
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆122Updated this week
- ☆46Updated 10 months ago
- A lightweight design for computation-communication overlap.☆182Updated 3 weeks ago
- Magnum IO community repo☆100Updated 2 months ago
- Unified Collective Communication Library☆278Updated this week
- oneAPI Collective Communications Library (oneCCL)☆244Updated last week
- [DEPRECATED] Moved to ROCm/rocm-systems repo☆84Updated this week
- ☆93Updated 11 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆358Updated 2 weeks ago
- ☆83Updated 2 years ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆186Updated 9 months ago
- GVProf: A Value Profiler for GPU-based Clusters☆52Updated last year
- Synthesizer for optimal collective communication algorithms☆118Updated last year
- A language and compiler for irregular tensor programs.☆149Updated 11 months ago
- Thunder Research Group's Collective Communication Library☆42Updated 3 months ago
- A hierarchical collective communications library with portable optimizations☆36Updated 10 months ago