Alternatives and similar repositories for nccl-tests

Users that are interested in nccl-tests are comparing it to the libraries listed below

• NVIDIA / nvbandwidth
  A tool for bandwidth measurements on NVIDIA GPUs.
  ☆610Updated 9 months ago
• NVIDIA / DCGM
  NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs
  ☆654Updated last month
• ai-dynamo / nixl
  NVIDIA Inference Xfer Library (NIXL)
  ☆844Updated last week
• volcengine / veScale
  Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
  ☆923Updated 2 months ago
• NVIDIA / nccl
  Optimized primitives for collective multi-GPU communication
  ☆4,416Updated this week
• Mellanox / nv_peer_memory
  ☆384Updated last year
• NVIDIA / gdrcopy
  A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology
  ☆1,331Updated last month
• Mellanox / nccl-rdma-sharp-plugins
  RDMA and SHARP plugins for nccl library
  ☆221Updated 2 weeks ago
• pytorch / kineto
  A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
  ☆919Updated this week
• ByteDance-Seed / Triton-distributed
  Distributed Compiler based on Triton for Parallel Systems
  ☆1,322Updated last month
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆772Updated 9 months ago
• microsoft / superbenchmark
  A validation and profiling tool for AI infrastructure
  ☆359Updated this week
• microsoft / mscclpp
  MSCCL++: A GPU-driven communication stack for scalable AI applications
  ☆455Updated this week
• NVIDIA / multi-gpu-programming-models
  Examples demonstrating available options to program multiple GPUs in a single node or a cluster
  ☆862Updated 4 months ago
• microsoft / msccl
  Microsoft Collective Communication Library
  ☆379Updated 2 years ago
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆449Updated 8 months ago
• linux-rdma / perftest
  Infiniband Verbs Performance Tests
  ☆905Updated 3 weeks ago
• bytedance / flux
  A fast communication-overlapping library for tensor/expert parallelism on GPUs.
  ☆1,235Updated 5 months ago
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆497Updated 10 months ago
• NVIDIA / TransformerEngine
  A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…
  ☆3,116Updated last week
• coreweave / nccl-tests
  NVIDIA NCCL Tests for Distributed Training
  ☆133Updated this week
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆523Updated 4 months ago
• NVIDIA / nvidia-resiliency-ext
  NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …
  ☆253Updated last week
• facebookresearch / HolisticTraceAnalysis
  A library to analyze PyTorch traces.
  ☆464Updated last week
• mlcommons / inference
  Reference implementations of MLPerf® inference benchmarks
  ☆1,522Updated this week
• pytorch / PiPPy
  Pipeline Parallelism for PyTorch
  ☆785Updated last year
• google / nccl-fastsocket
  NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.
  ☆122Updated 2 years ago
• aws / aws-ofi-nccl
  This is a plugin which lets EC2 developers use libfabric as network provider while running NCCL applications.
  ☆203Updated last week
• pytorch / gloo
  Collective communications library with various primitives for multi-machine training.
  ☆1,390Updated 2 weeks ago
• imbue-ai / cluster-health
  ☆321Updated last year