VUA stands for 'VAST Undivided Attention'. It's a global KVCache storage solution optimizing LLM time to first token (TTFT) and GPU utilization.
☆38Mar 12, 2026Updated 6 months ago
Alternatives and similar repositories for VUA
Users that are interested in VUA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- VASTPY is the official Python SDK for the VAST Management System☆21Mar 26, 2026Updated 5 months ago
- Python-based SDK designed for interacting with VAST Database & VAST Catalog, enabling schema and table management, efficient ingest, quer…☆39Apr 15, 2026Updated 5 months ago
- These are lab guides for our customer/partner training and lab environment☆20Apr 15, 2026Updated 5 months ago
- Python mocking and stubbing library☆19Oct 3, 2024Updated last year
- BS3: Block device in S3☆13Apr 19, 2022Updated 4 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Lustre Repository with MS patches☆16Updated this week
- Cray Lustre is HPE's curated Lustre distro for HPE ClusterStor, Cray EX, and other HPE/Cray clients☆18Updated this week
- ☆25Jun 24, 2022Updated 4 years ago
- ☆40Aug 6, 2026Updated last month
- BUSE: Block device in user space☆16Apr 19, 2022Updated 4 years ago
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆93Dec 7, 2025Updated 9 months ago
- This repository holds the source code for robinhood version 4, a suite of tools to store and query any filesystem's metadata.☆16Updated this week
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 2 months ago
- LSDN: Linux Software Defined Network☆27Oct 18, 2020Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Persist and reuse KV Cache to speedup your LLM.☆337Updated this week
- SGLang Kernel Wheel Index☆26Updated this week
- High-performance safetensors model loader☆167Sep 10, 2026Updated last week
- A TUI-based utility for real-time monitoring of InfiniBand traffic and performance metrics on the local node☆74May 16, 2026Updated 4 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated last year
- ☆21Jan 2, 2023Updated 3 years ago
- Public repository for the BeeGFS Parallel File System☆228Aug 19, 2026Updated last month
- Parse golang data structure into proto3.☆11Feb 6, 2018Updated 8 years ago
- KV cache store for distributed LLM inference☆444Sep 16, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- SPDK RocksDB mirror☆33Jul 31, 2024Updated 2 years ago
- Alibaba Cloud's high-performance KVCache system for LLM inference, with components for global cache management, inference simulation(HiSi…☆260Updated this week
- Mirror of official thekelleys repo, with extra work on branches☆13Nov 15, 2018Updated 7 years ago
- Making MongoDB queries fun again☆36Aug 4, 2012Updated 14 years ago
- MLPerf® Storage Benchmark Suite☆203Updated this week
- Fast and easy distributed model training examples.☆12Nov 26, 2024Updated last year
- STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth☆18Aug 21, 2023Updated 3 years ago
- Persistent Memory Test Suite☆14Apr 29, 2020Updated 6 years ago
- ☆12Aug 27, 2024Updated 2 years ago
- 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.
- ☆11Dec 20, 2022Updated 3 years ago
- ☆75Mar 26, 2025Updated last year
- ☆356Updated this week
- Translation layer that maps any Kubernetes framework's Custom Resource Definitions (CRDs) into a standardized, generic structure.☆74Updated this week
- Official Tinkerbell Roadmap☆11Jun 12, 2025Updated last year
- Prototyp MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism☆34Apr 4, 2025Updated last year
- NVIDIA Inference Xfer Library (NIXL)☆1,265Updated this week