SJTU-IPADS / disb
DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
☆52Updated 8 months ago
Alternatives and similar repositories for disb:
Users that are interested in disb are comparing it to the libraries listed below
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 2 years ago
- 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
- ☆37Updated 3 years ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆25Updated 3 months ago
- SOTA Learning-augmented Systems☆36Updated 2 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 11 months ago
- ☆48Updated 4 months ago
- ☆22Updated last year
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- ☆79Updated 2 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated last year
- ☆49Updated 2 years ago
- ☆19Updated 2 years ago
- ☆53Updated 4 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆40Updated 5 months ago
- ☆23Updated 2 years ago
- ☆16Updated 2 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆19Updated last week
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆25Updated last year
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆50Updated 11 months ago
- ☆24Updated last year
- An Optimizing Compiler for Recommendation Model Inference☆23Updated last year
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆53Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Updated last year
- Artifacts for our SIGCOMM'22 paper Muri☆41Updated last year
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆33Updated 11 months ago