EMDC-OS / power-aware-triton
Know Your Enemy To Save Cloud Energy: Energy-Performance Characterization of Machine Learning Serving (HPCA '23)
☆13Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for power-aware-triton
- ☆9Updated 10 months ago
- Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.☆38Updated last month
- Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)☆54Updated 7 months ago
- ☆23Updated last year
- ☆41Updated last year
- "JABAS: Joint Adaptive Batching and Automatic Scaling for DNN Training on Heterogeneous GPUs" (EuroSys '25)☆12Updated last month
- ☆12Updated last month
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆58Updated 3 weeks ago
- ☆23Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆111Updated 6 months ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆64Updated last year
- ☆24Updated last year
- ☆37Updated 3 years ago
- ☆39Updated last month
- ☆51Updated 3 years ago
- NeuPIMs Simulator☆54Updated 5 months ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆8Updated 8 months ago
- LLM serving cluster simulator☆81Updated 6 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- ☆18Updated 5 months ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆29Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆133Updated last month
- ☆33Updated last year
- FastFlow is a system that automatically detects CPU bottlenecks in deep learning training pipelines and resolves the bottlenecks with dat…☆25Updated last year
- PyTorch-UVM on super-large language models.☆14Updated 3 years ago
- ☆33Updated 6 months ago
- Hi-Speed DNN Training with Espresso: Unleashing the Full Potential of Gradient Compression with Near-Optimal Usage Strategies (EuroSys '2…☆15Updated last year
- ☆100Updated last month
- Justitia provides RDMA isolation between applications with diverse requirements.☆38Updated 2 years ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆85Updated last year