Communication patterns for AI, built on top of NCCL device and host APIs
☆73Oct 28, 2026Updated this week
Alternatives and similar repositories for nccl-extensions
Users that are interested in nccl-extensions are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Updated this week
- NVIDIA Attribution☆31Updated this week
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆26Aug 5, 2026Updated 2 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆602Updated this week
- TensorIR is a lightweight NVIDIA-owned MLIR compiler frontend for expressing tensor computations and lowering them to NVIDIA CUDA Tile IR…☆141Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Triton-based Symmetric Memory operators and examples☆113May 15, 2026Updated 5 months ago
- InfiniCCL is a unified, cross-platform collective communication library designed for heterogeneous accelerator environments.☆21Updated this week
- NCCL Profiling Kit☆156Jul 1, 2024Updated 2 years ago
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 8 months ago
- High-performance RDMA for Python and PyTorch (ibverbs, efa, NVMe-oF)☆14Sep 2, 2026Updated 2 months ago
- Dist-MoE implements Speed-of-Light distributed Mixture-of-Experts forward and backward kernels. They are highly optimized and fused comm-…☆68Updated this week
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated last month
- Experiments, results, and misc. scripts.☆34Oct 2, 2026Updated last month
- Production-ready MoE load balancing via real-time expert replication☆259Oct 15, 2026Updated 2 weeks ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Fused MoE kernel☆23Oct 23, 2026Updated last week
- Perplexity GPU Kernels☆614Nov 7, 2025Updated 11 months ago
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆122Dec 17, 2025Updated 10 months ago
- ☆53Oct 22, 2026Updated last week
- GPU-accelerated linear solvers based on the conjugate gradient (CG) method, supporting NVIDIA and AMD GPUs with GPU-aware MPI, NCCL, RCCL…☆16Sep 24, 2026Updated last month
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆208Feb 11, 2026Updated 8 months ago
- A lightweight library for xPU kernel JIT compilation☆439Updated this week
- (deprecated) torchcomms: a modern PyTorch communications API☆403Updated this week
- htop-like TUI for real-time RDMA network monitoring.☆126Oct 27, 2026Updated last week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ☆171Dec 27, 2024Updated last year
- ☆27Feb 27, 2026Updated 8 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆103Jan 16, 2026Updated 9 months ago
- Venus Collective Communication Library, supported by SII and Infrawaves.☆153Sep 3, 2026Updated 2 months ago
- Mixture-of-experts (MoE) training megakernel for NVL72s☆637Oct 1, 2026Updated last month
- https://arxiv.org/abs/2610.13990☆34Oct 15, 2026Updated 2 weeks ago
- A high-performance, RDMA-native data-plane library for large-scale heterogeneous memory pools, developed by the Tencent Astral Network Te…☆35Aug 6, 2026Updated 2 months ago
- ☆98Feb 5, 2026Updated 8 months ago
- ☆118Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆16Jul 19, 2026Updated 3 months ago
- ☆46Oct 15, 2025Updated last year
- ☆17Jan 31, 2026Updated 9 months ago
- Clangd for Ascend for Code Lint & Code Completion☆34Sep 29, 2026Updated last month
- A high-performance communication library for machine learning training and inference on Huawei Ascend NPUs.☆283Sep 30, 2026Updated last month
- nvloom is a set of tools designed to scalably test MNNVL fabrics.☆66Oct 19, 2026Updated 2 weeks ago
- ☆37Aug 7, 2025Updated last year