vast-data / VUALinks
VUA stands for 'VAST Undivided Attention'. It's a global KVCache storage solution optimizing LLM time to first token (TTFT) and GPU utilization.
☆37Updated 7 months ago
Alternatives and similar repositories for VUA
Users that are interested in VUA are comparing it to the libraries listed below
Sorting:
- Mirror of official Lustre development repository http://git.whamcloud.com/fs/lustre-release☆264Updated this week
- NVIDIA NCCL Tests for Distributed Training☆134Updated 2 weeks ago
- A tool to detect infrastructure issues on cloud native AI systems☆52Updated 4 months ago
- CUDA checkpoint and restore utility☆410Updated 4 months ago
- An I/O benchmark for deep Learning applications☆102Updated last month
- NVIDIA GPUDirect Storage Driver☆331Updated last month
- MLPerf® Storage Benchmark Suite☆173Updated last week
- GPUd automates monitoring, diagnostics, and issue identification for GPUs☆475Updated this week
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆365Updated this week
- Public repository for the BeeGFS Parallel File System☆191Updated last month
- A toolkit for discovering cluster network topology.☆96Updated last week
- NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs☆658Updated 2 months ago
- cricket is a virtualization solution for GPUs☆234Updated 5 months ago
- ☆71Updated 11 months ago
- ☆322Updated last year
- KV cache store for distributed LLM inference☆390Updated 2 months ago
- Systematic and comprehensive benchmarks for LLM systems.☆50Updated last week
- IO500 Storage Benchmark source code☆128Updated 3 months ago
- MIG Partition Editor for NVIDIA GPUs☆240Updated this week
- Lightweight daemon for monitoring CUDA runtime API calls with eBPF uprobes☆146Updated 10 months ago
- Infiniband Verbs Performance Tests☆908Updated 3 weeks ago
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆773Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆876Updated this week
- Health checks for Azure N- and H-series VMs.☆57Updated this week
- Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the…☆362Updated last week
- Hooked CUDA-related dynamic libraries by using automated code generation tools.☆172Updated 2 years ago
- A validation and profiling tool for AI infrastructure☆360Updated this week
- ☆43Updated last year
- ☆334Updated last week
- CloudAI Benchmark Framework☆83Updated this week