JF-D / ParcaeLinks
☆21Updated last year
Alternatives and similar repositories for Parcae
Users that are interested in Parcae are comparing it to the libraries listed below
Sorting:
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆20Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆69Updated 3 weeks ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆218Updated 3 months ago
- ☆124Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆31Updated last year
- ☆38Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆132Updated last year
- A resilient distributed training framework☆96Updated last year
- ☆75Updated 3 weeks ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆89Updated 2 years ago
- This repository is established to store personal notes and annotated papers during daily research.☆159Updated this week
- ☆23Updated last year
- ☆27Updated last year
- Stateful LLM Serving☆88Updated 8 months ago
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆48Updated 3 months ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- ☆79Updated 3 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆150Updated 9 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆55Updated last year
- LLM serving cluster simulator☆119Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆53Updated 2 years ago
- A framework for generating realistic LLM serving workloads☆76Updated last month
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆190Updated last year
- High performance Transformer implementation in C++.☆140Updated 9 months ago
- ☆57Updated 2 weeks ago
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆44Updated 2 months ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆34Updated 2 months ago
- Dynamic resources changes for multi-dimensional parallelism training☆29Updated 2 months ago