REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU scheduling.
☆108Dec 24, 2022Updated 3 years ago
Alternatives and similar repositories for reef
Users that are interested in reef are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆58Aug 21, 2024Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆43May 29, 2022Updated 4 years ago
- ☆53Dec 26, 2024Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆163Nov 26, 2025Updated 6 months ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆127May 9, 2022Updated 4 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.
- ☆38Jun 27, 2025Updated 11 months ago
- Artifacts for our NSDI'23 paper TGS☆97Jun 10, 2024Updated 2 years ago
- Model-less Inference Serving☆94Nov 4, 2023Updated 2 years ago
- Ths is a fast RDMA abstraction layer that works both in the kernel and user-space.☆59Nov 12, 2024Updated last year
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆174May 9, 2026Updated last month
- ☆15Aug 15, 2024Updated last year
- ☆26Oct 1, 2025Updated 8 months ago
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆24Mar 1, 2024Updated 2 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.
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Aug 6, 2025Updated 10 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆72May 1, 2024Updated 2 years ago
- ☆54Dec 13, 2022Updated 3 years ago
- ☆85Dec 2, 2022Updated 3 years ago
- ☆24Oct 31, 2023Updated 2 years ago
- This is a list of awesome edgeAI inference related papers.☆98Dec 21, 2023Updated 2 years ago
- Project Mitosis Introduction☆19Nov 13, 2022Updated 3 years ago
- Official implementation for the paper Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapp…☆14May 20, 2026Updated 3 weeks ago
- Multi-Instance-GPU profiling tool☆58Apr 16, 2023Updated 3 years ago
- 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.
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆20Feb 23, 2024Updated 2 years ago
- A graph-based distributed in-memory store that leverages efficient graph exploration to provide highly concurrent and low-latency queries…☆192Jan 4, 2026Updated 5 months ago
- An OS kernel module for fast **remote** fork using advanced datacenter networking (RDMA).☆72Feb 15, 2025Updated last year
- GPU-scheduler-for-deep-learning☆212Nov 5, 2020Updated 5 years ago
- FTPipe and related pipeline model parallelism research.☆44May 16, 2023Updated 3 years ago
- A tool for examining GPU scheduling behavior.☆96Aug 17, 2024Updated last year
- Deduplication over dis-aggregated memory for Serverless Computing☆14Mar 21, 2022Updated 4 years ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆1,002Sep 19, 2024Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆819Apr 6, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Fast In-memory Transaction Processing using RDMA and HTM☆59Dec 20, 2015Updated 10 years ago
- A low-latency & high-throughput serving engine for LLMs☆506Jan 8, 2026Updated 5 months ago
- An efficient GPU resource sharing system with fine-grained control for Linux platforms.☆89Mar 25, 2024Updated 2 years ago
- libsmctrl论文的复现，添加了python端接口，可以在python端灵活调用接口来分配计算资源☆12May 21, 2024Updated 2 years ago
- Nu is a new datacenter system that enables developers to build fungible applications that can use datacenter resources wherever they are.☆42May 14, 2024Updated 2 years ago
- ☆200Aug 31, 2019Updated 6 years ago
- ☆38Jan 15, 2021Updated 5 years ago