Alternatives and similar repositories for aiperf

Users that are interested in aiperf are comparing it to the libraries listed below

• ai-dynamo / aiconfigurator
  Offline optimization of your disaggregated Dynamo graph
  ☆88Updated this week
• coreweave / nccl-tests
  NVIDIA NCCL Tests for Distributed Training
  ☆116Updated last week
• fmperf-project / fmperf
  Cloud Native Benchmarking of Foundation Models
  ☆44Updated 3 months ago
• sgl-project / genai-bench
  Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…
  ☆222Updated last week
• sgl-project / ome
  OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)
  ☆298Updated this week
• Azure / msccl
  Microsoft Collective Communication Library
  ☆66Updated 11 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 …
  ☆228Updated last week
• NVIDIA / cuda-checkpoint
  CUDA checkpoint and restore utility
  ☆377Updated last month
• ai-dynamo / nixl
  NVIDIA Inference Xfer Library (NIXL)
  ☆688Updated this week
• microsoft / NPKit
  NCCL Profiling Kit
  ☆145Updated last year
• Azure / msccl-executor-nccl
  ☆46Updated 10 months ago
• LMCache / LMBenchmark
  Systematic and comprehensive benchmarks for LLM systems.
  ☆38Updated last month
• foundation-model-stack / fastsafetensors
  High-performance safetensors model loader
  ☆70Updated last week
• ovg-project / kvcached
  Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
  ☆469Updated this week
• google / nccl-fastsocket
  NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.
  ☆121Updated last year
• aws / aws-ofi-nccl
  This is a plugin which lets EC2 developers use libfabric as network provider while running NCCL applications.
  ☆189Updated last week
• simon-mo / vLLM-Benchmark
  ☆31Updated 6 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆96Updated last week
• antgroup / DeepXTrace
  DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.
  ☆63Updated last week
• argonne-lcf / dlio_benchmark
  An I/O benchmark for deep Learning applications
  ☆91Updated last week
• IBM / autopilot
  A tool to detect infrastructure issues on cloud native AI systems
  ☆49Updated last month
• facebookresearch / param
  PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for…
  ☆153Updated 2 weeks ago
• abcdabcd987 / libfabric-efa-demo
  ☆65Updated 9 months ago
• meta-pytorch / torchcomms
  torchcomms: a modern PyTorch communications API
  ☆219Updated this week
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆182Updated 3 weeks ago
• NVIDIA / nvbandwidth
  A tool for bandwidth measurements on NVIDIA GPUs.
  ☆553Updated 6 months ago
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆502Updated last month
• volcengine / veTurboIO
  A library developed by Volcano Engine for high-performance reading and writing of PyTorch model files.
  ☆24Updated 9 months ago
• bytedance / InfiniStore
  KV cache store for distributed LLM inference
  ☆346Updated last month
• ParCoreLab / Snoopie
  Multi-GPU communication profiler and visualizer
  ☆36Updated last year