SamsungLabs / FastFlow
FastFlow is a system that automatically detects CPU bottlenecks in deep learning training pipelines and resolves the bottlenecks with data pipeline offloading to remote resources .
☆25Updated last year
Related projects: ⓘ
- Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)☆51Updated 5 months ago
- ☆40Updated last year
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆32Updated last month
- An interference-aware scheduler for fine-grained GPU sharing☆92Updated 4 months ago
- ☆48Updated 3 years ago
- Compiler for Dynamic Neural Networks☆42Updated 10 months ago
- ☆22Updated 2 years ago
- ☆12Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- ☆34Updated 3 years ago
- ☆20Updated 10 months ago
- ☆19Updated last year
- SOTA Learning-augmented Systems☆32Updated 2 years ago
- LLM serving cluster simulator☆55Updated 4 months ago
- ☆37Updated 2 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆46Updated 3 weeks ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆55Updated 4 months ago
- ☆16Updated 3 months ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆28Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆51Updated 4 months ago
- ☆45Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆54Updated 3 months ago
- ☆32Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆84Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆43Updated 2 months ago
- ☆29Updated 6 months ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆39Updated 2 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆8Updated 6 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆46Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆76Updated last year