quiver-team / quiver-featureLinks
High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph
☆55Updated 3 years ago
Alternatives and similar repositories for quiver-feature
Users that are interested in quiver-feature are comparing it to the libraries listed below
Sorting:
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated last year
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆31Updated 6 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆60Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- My paper/code reading notes in Chinese☆46Updated 2 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆99Updated 2 years ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆35Updated 2 years ago
- Dorylus: Affordable, Scalable, and Accurate GNN Training☆76Updated 4 years ago
- A Factored System for Sample-based GNN Training over GPUs☆42Updated 2 years ago
- ☆22Updated last year
- ☆27Updated 6 months ago
- Artifact of ASPLOS'23 paper entitled: GRACE: A Scalable Graph-Based Approach to Accelerating Recommendation Model Inference☆19Updated 2 years ago
- Stateful LLM Serving☆81Updated 5 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- FGNN's artifact evaluation (EuroSys 2022)☆17Updated 3 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆84Updated 2 years ago
- Vector search with bounded performance.☆36Updated last year
- ☆13Updated 2 years ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆104Updated 3 months ago
- ☆55Updated 4 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆22Updated 3 months ago
- Model-less Inference Serving☆91Updated last year
- PetPS: Supporting Huge Embedding Models with Tiered Memory☆32Updated last year
- ☆36Updated last year
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆24Updated last year
- ☆17Updated 2 years ago