SJTU-IPADS / reefLinks
REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU scheduling.
☆99Updated 2 years ago
Alternatives and similar repositories for reef
Users that are interested in reef 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
- ☆50Updated 7 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆143Updated 6 months ago
- ☆37Updated last month
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated last year
- ☆51Updated 2 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆60Updated last year
- Artifacts for our NSDI'23 paper TGS☆82Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- ☆22Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆84Updated 2 years ago
- ☆80Updated 2 years ago
- Artifacts for our SIGCOMM'22 paper Muri☆42Updated last year
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆119Updated 3 weeks ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- ☆42Updated 2 months ago
- LLM serving cluster simulator☆108Updated last year
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆75Updated 2 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆60Updated 9 months ago
- ☆24Updated 3 years ago
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆55Updated 2 years ago
- ☆38Updated last year
- ☆75Updated 3 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆29Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆198Updated last month
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆87Updated 2 weeks ago
- SOTA Learning-augmented Systems☆36Updated 3 years ago