Linestro / GRACELinks
Artifact of ASPLOS'23 paper entitled: GRACE: A Scalable Graph-Based Approach to Accelerating Recommendation Model Inference
☆18Updated 2 years ago
Alternatives and similar repositories for GRACE
Users that are interested in GRACE are comparing it to the libraries listed below
Sorting:
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆27Updated 4 months ago
- ☆30Updated last year
- ☆23Updated 2 years ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆52Updated last year
- ☆18Updated 4 years ago
- ☆16Updated 2 years ago
- An Optimizing Compiler for Recommendation Model Inference☆24Updated 2 weeks ago
- ☆34Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 10 months ago
- High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph☆54Updated 2 years ago
- ☆25Updated last year
- ☆9Updated last year
- Artifact for OSDI'23: MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Mult…☆39Updated last year
- ☆27Updated 4 years ago
- Sharing the codebase and steps for artifact evaluation/reproduction for MICRO 2024 paper☆9Updated 9 months ago
- ☆36Updated last year
- Horizontal Fusion☆24Updated 3 years ago
- ☆37Updated 2 years ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- ☆22Updated 2 years ago
- GVProf: A Value Profiler for GPU-based Clusters☆50Updated last year
- This serves as a repository for reproducibility of the SC21 paper "In-Depth Analyses of Unified Virtual Memory System for GPU Accelerated…☆32Updated last year
- Thinking is hard - automate it☆19Updated 2 years ago
- ☆22Updated last year
- A source-to-source compiler for optimizing CUDA dynamic parallelism by aggregating launches☆15Updated 6 years ago
- ☆7Updated 4 years ago
- ☆79Updated 2 years ago
- ☆28Updated 11 months ago
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated 7 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year