asplos-contest / 2025
The ASPLOS 2025 / EuroSys 2025 Contest Track
☆30Updated this week
Alternatives and similar repositories for 2025:
Users that are interested in 2025 are comparing it to the libraries listed below
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 3 months ago
- ☆76Updated 2 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆18Updated last week
- ASPLOS'24: Optimal Kernel Orchestration for Tensor Programs with Korch☆32Updated this week
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆49Updated 10 months ago
- Horizontal Fusion☆22Updated 3 years ago
- ☆34Updated 8 months ago
- ☆22Updated 8 months ago
- ☆23Updated last year
- Compiler for Dynamic Neural Networks☆45Updated last year
- ☆27Updated 8 months ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆72Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆94Updated 2 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆28Updated 4 months ago
- ☆9Updated 5 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated 10 months ago
- Microsoft Collective Communication Library☆60Updated 4 months ago
- ☆18Updated 10 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 9 months ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated last year
- Thunder Research Group's Collective Communication Library☆35Updated 11 months ago
- ☆92Updated 2 years ago
- ☆10Updated 2 years ago
- ☆36Updated 4 months ago
- High performance Transformer implementation in C++.☆111Updated 2 months ago
- Stateful LLM Serving☆50Updated 2 weeks ago
- ☆36Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆49Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆156Updated 5 months ago
- ☆69Updated 3 years ago