EMDC-OS / power-aware-tritonLinks
Know Your Enemy To Save Cloud Energy: Energy-Performance Characterization of Machine Learning Serving (HPCA '23)
☆13Updated 2 months ago
Alternatives and similar repositories for power-aware-triton
Users that are interested in power-aware-triton are comparing it to the libraries listed below
Sorting:
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated 3 weeks ago
- Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.☆38Updated 2 months ago
- ☆50Updated 8 months ago
- ☆25Updated 2 years ago
- MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant GPU Clusters☆20Updated 2 years ago
- ☆73Updated 3 months ago
- ☆37Updated 2 months ago
- ☆12Updated 4 months ago
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆135Updated last month
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆75Updated 2 years ago
- ☆24Updated 3 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Updated last year
- Network Contention-Aware Cluster Scheduling with Reinforcement Learning (IEEE ICPADS'23)☆16Updated last month
- An interference-aware scheduler for fine-grained GPU sharing☆145Updated 7 months ago
- ☆25Updated 2 years ago
- Repository for MLCommons Chakra schema and tools☆120Updated last month
- LaLaRAND: Flexible Layer-by-Layer CPU/GPU Scheduling for Real-Time DNN Tasks☆15Updated 3 years ago
- ☆29Updated last week
- Synthesizer for optimal collective communication algorithms☆116Updated last year
- LLM serving cluster simulator☆108Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆200Updated last month
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆15Updated 4 years ago
- ☆50Updated 2 months ago
- Microsoft Collective Communication Library☆359Updated last year
- ☆81Updated 2 years ago
- Hi-Speed DNN Training with Espresso: Unleashing the Full Potential of Gradient Compression with Near-Optimal Usage Strategies (EuroSys '2…☆15Updated last year
- ☆20Updated 8 months ago
- Releasing the spot availability traces used in "Can't Be Late" paper.☆23Updated last year
- This serves as a repository for reproducibility of the SC21 paper "In-Depth Analyses of Unified Virtual Memory System for GPU Accelerated…☆35Updated last year
- ☆38Updated 4 years ago