ml-energy / zeus
Deep Learning Energy Measurement and Optimization
☆218Updated this week
Related projects ⓘ
Alternatives and complementary repositories for zeus
- How much energy do GenAI models consume?☆41Updated last month
- A resilient distributed training framework☆85Updated 7 months ago
- A large-scale simulation framework for LLM inference☆277Updated last month
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…☆146Updated 2 weeks ago
- A library to analyze PyTorch traces.☆308Updated this week
- Microsoft Collective Communication Library☆54Updated last month
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆112Updated 8 months ago
- Efficient and easy multi-instance LLM serving☆216Updated this week
- Multi-Instance-GPU profiling tool☆53Updated last year
- Making Long-Context LLM Inference 10x Faster and 10x Cheaper☆236Updated this week
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆101Updated 9 months ago
- Fast Inference of MoE Models with CPU-GPU Orchestration☆172Updated this week
- A low-latency & high-throughput serving engine for LLMs☆245Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆166Updated 3 weeks ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago
- ☆46Updated 5 months ago
- CUDA checkpoint and restore utility☆226Updated 7 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆111Updated 6 months ago
- ☆237Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆133Updated last month
- This repository contains the experimental PyTorch native float8 training UX☆211Updated 3 months ago
- extensible collectives library in triton☆72Updated last month
- ☆38Updated 4 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆165Updated this week
- ACT An Architectural Carbon Modeling Tool for Designing Sustainable Computer Systems☆34Updated 2 years ago
- Cloud Native Benchmarking of Foundation Models☆20Updated 2 weeks ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆250Updated this week
- Fast Hadamard transform in CUDA, with a PyTorch interface☆111Updated 5 months ago
- Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)☆54Updated 7 months ago
- LLM Serving Performance Evaluation Harness☆56Updated 2 months ago