Sys-KU / DeepPlanLinks
[ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access
☆56Updated last year
Alternatives and similar repositories for DeepPlan
Users that are interested in DeepPlan are comparing it to the libraries listed below
Sorting:
- ☆23Updated 2 years ago
- ☆53Updated 4 years ago
- ☆25Updated last year
- ☆49Updated 5 months ago
- ☆37Updated 3 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆94Updated 2 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆50Updated 2 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- ☆49Updated 2 years ago
- LLM serving cluster simulator☆100Updated last year
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- ☆22Updated last year
- ☆36Updated 4 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated last year
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆117Updated 3 months ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated 11 months ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆33Updated 2 years ago
- Multi-Instance-GPU profiling tool☆58Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆137Updated 4 months ago
- ☆79Updated 2 years ago
- [USENIX ATC '21] Exploring the Design Space of Page Management for Multi-Tiered Memory Systems☆45Updated 3 years ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆19Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆171Updated 7 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Honorable Mention]☆10Updated 2 months ago
- ☆23Updated 10 months ago
- ☆36Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 9 months ago