ml-energy / zeusLinks
Measure and optimize the energy consumption of your AI applications!
☆326Updated last month
Alternatives and similar repositories for zeus
Users that are interested in zeus are comparing it to the libraries listed below
Sorting:
- A canonical source of GenAI energy benchmark and meausrements☆50Updated last month
- ACT An Architectural Carbon Modeling Tool for Designing Sustainable Computer Systems☆44Updated 5 months ago
- A resilient distributed training framework☆96Updated last year
- Microsoft Collective Communication Library☆66Updated last year
- torchcomms: a modern PyTorch communications API☆315Updated this week
- A large-scale simulation framework for LLM inference☆507Updated 5 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆268Updated 2 months ago
- A low-latency & high-throughput serving engine for LLMs☆459Updated 2 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆253Updated last year
- Multi-Instance-GPU profiling tool☆58Updated 2 years ago
- PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for…☆154Updated 3 weeks ago
- A library to analyze PyTorch traces.☆453Updated 2 weeks ago
- LLM Serving Performance Evaluation Harness☆82Updated 10 months ago
- Perplexity open source garden for inference technology☆321Updated last week
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆226Updated 5 months ago
- Carbon Explorer helps evaluating solutions make datacenters operate on renewable energy.☆86Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Updated last year
- Stateful LLM Serving☆92Updated 9 months ago
- 🔮 Execution time predictions for deep neural network training iterations across different GPUs.☆63Updated 3 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆158Updated last month
- Modyn is a research-platform for training ML models on growing datasets.☆51Updated 7 months ago
- Fast low-bit matmul kernels in Triton☆416Updated 2 weeks ago
- ☆80Updated 2 months ago
- ☆144Updated last year
- A schedule language for large model training☆152Updated 4 months ago
- 🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.☆64Updated 11 months ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Updated last year
- A framework for generating realistic LLM serving workloads☆94Updated 2 months ago
- Model-less Inference Serving☆92Updated 2 years ago
- LLM KV cache compression made easy☆734Updated 2 weeks ago