rccl

GPU-accelerated linear solvers based on the conjugate gradient (CG) method, supporting NVIDIA and AMD GPUs with GPU-aware MPI, NCCL, RCCL or NVSHMEM

Multi-GPU tensor-parallel vLLM on AMD Radeon RX 7900 XT / XTX / GRE (7900XT, 7900XTX, RX7900XT, gfx1100, RDNA3, ROCm): root cause and fix for the RCCL hostcall / PCIe atomics (AtomicOps) crash "NCCL error: unhandled cuda error" / "operation cannot be performed in the present state", Proxmox VFIO passthrough; LLM inference benchmarks on 13 machines

Tool to run rccl-tests/nccl-tests based on from an application and gather performance.

Interactive web visualization for understanding collective communication algorithms (as used in NCCL, RCCL, MPI). Learn how AllReduce, Broadcast, Reduce, AllGather and more work step by step.

Pure-Python drop-in subset of Ray's API that makes vLLM distributed inference work across nodes. ~1,400 LoC, one dependency, bind-mount into the stock vLLM image. NVIDIA + AMD, validated cross-node.

Native Windows AMD multi-GPU bridge for vLLM and llama.cpp/ROCmFPX via Direct-RCCL, D3D12, and hybrid routing

Distributed Deep Learning (DL) proxy benchmark.

Royal Caribbean custom integration for Home Assistant