JF-D / Parcae
☆12Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for Parcae
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆14Updated 11 months ago
- Compiler for Dynamic Neural Networks☆43Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆132Updated last month
- ☆56Updated 2 years ago
- ☆14Updated 5 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- ☆52Updated last week
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆78Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- ☆23Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆8Updated 8 months ago
- ☆37Updated 3 years ago
- ☆15Updated 4 months ago
- ☆41Updated last year
- LLM serving cluster simulator☆81Updated 6 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆85Updated last year
- ☆46Updated 5 months ago
- ☆12Updated last year
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny model can tell you the verbosity of an LLM (…☆22Updated 5 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆79Updated 4 months ago
- ☆30Updated 4 months ago
- nnScaler: Compiling DNN models for Parallel Training☆74Updated 3 weeks ago
- ☆73Updated last year
- A resilient distributed training framework☆85Updated 7 months ago
- An experimental parallel training platform☆52Updated 7 months ago
- ☆48Updated last year
- This repository is established to store personal notes and annotated papers during daily research.☆89Updated this week
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆101Updated 8 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆15Updated 6 months ago