SpotServe: Serving Generative Large Language Models on Preemptible Instances
☆136Feb 22, 2024Updated 2 years ago
Alternatives and similar repositories for SpotServe
Users that are interested in SpotServe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Disaggregated serving system for Large Language Models (LLMs).☆829Apr 6, 2025Updated last year
- ☆135Nov 11, 2024Updated last year
- A low-latency & high-throughput serving engine for LLMs☆518Jan 8, 2026Updated 7 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆223Sep 21, 2024Updated last year
- ☆22Apr 22, 2024Updated 2 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.
- Serverless LLM Serving for Everyone.☆700May 4, 2026Updated 3 months ago
- Efficient and easy multi-instance LLM serving☆563Mar 12, 2026Updated 5 months ago
- Releasing the spot availability traces used in "Can't Be Late" paper.☆27Mar 31, 2024Updated 2 years ago
- ☆91Oct 17, 2025Updated 9 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆24Nov 21, 2024Updated last year
- Predict the performance of LLM inference services☆23Sep 18, 2025Updated 10 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆37May 6, 2024Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆284Jun 30, 2026Updated last month
- An interference-aware scheduler for fine-grained GPU sharing☆164Nov 26, 2025Updated 8 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A throughput-oriented high-performance serving framework for LLMs☆974Mar 29, 2026Updated 4 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆94Jul 14, 2023Updated 3 years ago
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆55Dec 11, 2022Updated 3 years ago
- ☆48Jun 27, 2024Updated 2 years ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,898Updated this week
- ☆10Jul 23, 2024Updated 2 years ago
- Accurate, large-scale, and extensible simulator for LLM inference Systems☆664Jul 25, 2025Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆58Aug 21, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆94Oct 15, 2025Updated 10 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- LLM serving cluster simulator☆157Apr 25, 2024Updated 2 years ago
- LLM Serving Performance Evaluation Harness☆84Feb 25, 2025Updated last year
- Artifact for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆46Nov 24, 2022Updated 3 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆65Jun 5, 2024Updated 2 years ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆93May 23, 2023Updated 3 years ago
- Virtual Memory Abstraction for Serverless Architectures☆49Mar 18, 2022Updated 4 years ago
- Stateful LLM Serving☆105Mar 11, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Artifacts for our ASPLOS'23 paper ElasticFlow☆57May 10, 2024Updated 2 years ago
- ☆170Oct 9, 2024Updated last year
- ☆335Jan 22, 2024Updated 2 years ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆39Aug 29, 2025Updated 11 months ago
- Artifacts for our SIGCOMM'22 paper Muri☆44Dec 29, 2023Updated 2 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆127May 9, 2022Updated 4 years ago
- Microsoft Azure Traces☆1,176Jun 3, 2026Updated 2 months ago