SJTU-IPADS / disb
DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
☆53Updated 7 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…☆93Updated 2 years ago
- ☆37Updated 3 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 10 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 9 months ago
- ☆23Updated last year
- Compiler for Dynamic Neural Networks☆45Updated last year
- ☆47Updated 2 months ago
- ☆23Updated 2 years ago
- ☆75Updated 2 years ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆20Updated last month
- My paper/code reading notes in Chinese☆46Updated 10 months ago
- SOTA Learning-augmented Systems☆35Updated 2 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆127Updated 2 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated 10 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆82Updated last year
- ☆49Updated 2 years ago
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 3 months ago
- ☆16Updated 2 years ago
- An Optimizing Compiler for Recommendation Model Inference☆23Updated last year
- ☆53Updated 4 years ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆49Updated 9 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆153Updated 5 months ago
- Stateful LLM Serving☆48Updated last week
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- ☆42Updated 10 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆129Updated last month
- ☆24Updated last year
- Model-less Inference Serving☆85Updated last year