[ICML 2024] Serving LLMs on heterogeneous decentralized clusters.
☆37May 6, 2024Updated 2 years ago
Alternatives and similar repositories for HexGen
Users that are interested in HexGen are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Accommodating Large Language Model Training over Heterogeneous Environment.☆30Mar 13, 2025Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆88Oct 15, 2025Updated 7 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Feb 22, 2024Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆162Nov 26, 2025Updated 5 months ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆39Aug 29, 2025Updated 8 months ago
- 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.
- ☆47Jun 27, 2024Updated last year
- Accurate, large-scale, and extensible simulator for LLM inference Systems☆601Jul 25, 2025Updated 9 months ago
- A resilient distributed training framework☆100Apr 11, 2024Updated 2 years ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆20Feb 23, 2024Updated 2 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Mar 7, 2024Updated 2 years ago
- This repository is established to store personal notes and annotated papers during daily research.☆194Updated this week
- ☆27Aug 31, 2023Updated 2 years ago
- Galvatron is an automatic distributed training system designed for Transformer models, including Large Language Models (LLMs). If you hav…☆24Oct 22, 2025Updated 6 months ago
- ☆133Nov 11, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆24Mar 1, 2024Updated 2 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆56May 10, 2024Updated 2 years ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆18Jul 10, 2025Updated 10 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆55Dec 11, 2022Updated 3 years ago
- ☆24Aug 15, 2023Updated 2 years ago
- A low-latency & high-throughput serving engine for LLMs☆497Jan 8, 2026Updated 4 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆187Jul 10, 2024Updated last year
- Host CIFAR-10.2 Data Set☆13Sep 22, 2021Updated 4 years ago
- APEX+ is an LLM Serving Simulator☆46Jun 16, 2025Updated 11 months ago
- 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.
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆79Nov 4, 2024Updated last year
- ☆34Apr 8, 2025Updated last year
- ☆17May 10, 2024Updated 2 years ago
- ☆91Oct 17, 2025Updated 7 months ago
- DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting☆18Mar 4, 2025Updated last year
- ☆19May 4, 2023Updated 3 years ago
- Proof of concept, using Sysdig metrics as the decision variable for a Kubernetes scheduler☆14Nov 3, 2017Updated 8 years ago
- A throughput-oriented high-performance serving framework for LLMs☆959Mar 29, 2026Updated last month
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆92May 23, 2023Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆94Jul 14, 2023Updated 2 years ago
- ☆26Mar 14, 2024Updated 2 years ago
- Efficient and easy multi-instance LLM serving☆549Mar 12, 2026Updated 2 months ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆44Nov 4, 2022Updated 3 years ago
- ☆13Feb 22, 2023Updated 3 years ago
- Code for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020☆138Jul 25, 2024Updated last year
- ☆13May 14, 2026Updated last week