SJTU-IPADS / disbLinks
DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.
☆52Updated 10 months ago
Alternatives and similar repositories for disb
Users that are interested in disb are comparing it to the libraries listed below
Sorting:
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆95Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- ☆37Updated 2 weeks ago
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆27Updated 5 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- ☆54Updated 4 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- ☆25Updated last year
- My paper/code reading notes in Chinese☆46Updated last month
- ☆24Updated 2 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆20Updated 2 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆82Updated last year
- Model-less Inference Serving☆88Updated last year
- ☆14Updated 3 years ago
- ☆49Updated 6 months ago
- ☆79Updated 2 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆53Updated 7 months ago
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 2 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆50Updated 2 years ago
- ☆51Updated 2 years ago
- An experimental parallel training platform☆54Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆35Updated 2 years ago
- ☆22Updated last year
- Multi-Instance-GPU profiling tool☆60Updated 2 years ago
- ☆16Updated last year
- LLM serving cluster simulator☆107Updated last year