ml-energy / zeus
Deep Learning Energy Measurement and Optimization
☆193Updated last week
Related projects: ⓘ
- How much energy do LLMs consume?☆40Updated last week
- A resilient distributed training framework☆78Updated 5 months ago
- Efficient serverless deployment for large AI models.☆178Updated this week
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- A large-scale simulation framework for LLM inference☆236Updated 3 weeks ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆144Updated this week
- A low-latency & high-throughput serving engine for LLMs☆174Updated last week
- Fast Inference of MoE Models with CPU-GPU Orchestration☆163Updated 3 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆106Updated 6 months ago
- ☆234Updated last month
- This repository contains the experimental PyTorch native float8 training UX☆210Updated last month
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆90Updated last month
- ACT An Architectural Carbon Modeling Tool for Designing Sustainable Computer Systems☆33Updated last year
- A performant, memory-efficient checkpointing library for PyTorch applications, designed with large, complex distributed workloads in mind…☆145Updated this week
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆92Updated 6 months ago
- ML model training for edge devices☆158Updated 11 months ago
- Applied AI experiments and examples for PyTorch☆123Updated last month
- ☆35Updated 2 months ago
- ☆32Updated this week
- A library to analyze PyTorch traces.☆270Updated last week
- Multi-Instance-GPU profiling tool☆51Updated last year
- Latency and Memory Analysis of Transformer Models for Training and Inference☆338Updated 3 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆156Updated this week
- CUDA checkpoint and restore utility☆193Updated 5 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆76Updated last year
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆166Updated 11 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆92Updated 4 months ago
- A curated list of awesome projects and papers for distributed training or inference☆189Updated last month
- ☆47Updated 3 weeks ago
- A minimal implementation of vllm.☆29Updated last month