SJTU-IPADS / ugache
☆23Updated last year
Alternatives and similar repositories for ugache:
Users that are interested in ugache are comparing it to the libraries listed below
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆92Updated 2 years ago
- Compiler for Dynamic Neural Networks☆45Updated last year
- ☆36Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 10 months ago
- ☆69Updated 3 years ago
- ☆23Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 9 months ago
- ☆18Updated 9 months ago
- ☆75Updated 2 years ago
- ☆8Updated 2 years ago
- ☆31Updated last year
- Artifact for OSDI'23: MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Mult…☆41Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 2 years ago
- Dorylus: Affordable, Scalable, and Accurate GNN Training☆78Updated 3 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- ☆37Updated 3 years ago
- ☆49Updated 2 years ago
- ☆46Updated 2 months ago
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆23Updated last year
- A Factored System for Sample-based GNN Training over GPUs☆42Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- FGNN's artifact evaluation (EuroSys 2022)☆17Updated 2 years ago
- ☆32Updated 9 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆19Updated 3 months ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆31Updated 2 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated 10 months ago
- Artifacts for our SIGCOMM'22 paper Muri☆41Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 7 months ago
- PetPS: Supporting Huge Embedding Models with Tiered Memory☆30Updated 10 months ago