alpa-projects / mmsLinks
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
☆91Updated 2 years ago
Alternatives and similar repositories for mms
Users that are interested in mms are comparing it to the libraries listed below
Sorting:
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆220Updated 4 months ago
- Compiler for Dynamic Neural Networks☆46Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆54Updated 2 years ago
- LLM serving cluster simulator☆122Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆55Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆132Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆73Updated last month
- A resilient distributed training framework☆96Updated last year
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- ☆27Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆103Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆153Updated last week
- ☆83Updated 3 years ago
- ☆79Updated 3 years ago
- ☆79Updated last month
- This repository is established to store personal notes and annotated papers during daily research.☆165Updated this week
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆137Updated last month
- An experimental parallel training platform☆56Updated last year
- ☆23Updated last year
- ☆51Updated 2 years ago
- ☆38Updated 5 months ago
- ☆124Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆65Updated last year
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆53Updated 3 months ago
- Stateful LLM Serving☆89Updated 8 months ago
- Dynamic resources changes for multi-dimensional parallelism training☆29Updated 3 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆31Updated last year
- A framework for generating realistic LLM serving workloads☆87Updated last month
- ☆57Updated 4 years ago