HabanaAI / hccl_demoLinks
☆24Updated last month
Alternatives and similar repositories for hccl_demo
Users that are interested in hccl_demo are comparing it to the libraries listed below
Sorting:
- A high-throughput and memory-efficient inference and serving engine for LLMs☆85Updated last week
- 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
- ☆22Updated last month
- RCCL Performance Benchmark Tests☆79Updated last week
- oneAPI Collective Communications Library (oneCCL)☆247Updated last month
- MAD (Model Automation and Dashboarding)☆30Updated last week
- SYCL* Templates for Linear Algebra (SYCL*TLA) - SYCL based CUTLASS implementation for Intel GPUs☆55Updated this week
- Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs☆12Updated 7 months ago
- Reference implementations of MLPerf™ HPC training benchmarks☆49Updated 9 months ago
- ☆51Updated this week
- A hierarchical collective communications library with portable optimizations☆36Updated 11 months ago
- ROCm Communication Collectives Library (RCCL)☆400Updated this week
- Bandwidth test for ROCm☆69Updated last week
- oneAPI Level Zero Conformance & Performance test content☆57Updated last week
- oneCCL Bindings for Pytorch* (deprecated)☆103Updated 3 weeks ago
- NCCL Profiling Kit☆149Updated last year
- Microsoft Collective Communication Library☆66Updated last year
- ☆63Updated last week
- Ongoing research training transformer models at scale☆33Updated this week
- ☆377Updated last year
- NVIDIA NCCL Tests for Distributed Training☆124Updated 2 weeks ago
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆23Updated last week
- ☆17Updated 2 months ago
- This repository contains the results and code for the MLPerf™ Training v2.0 benchmark.☆29Updated last year
- CloudAI Benchmark Framework☆74Updated this week
- rocSHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆129Updated this week
- Unified Collective Communication Library☆279Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆437Updated this week
- A tool for bandwidth measurements on NVIDIA GPUs.☆571Updated 7 months ago
- OpenVINO LLM Benchmark☆11Updated last year