ml-energy / zeusLinks
Measure and optimize the energy consumption of your AI applications!
☆318Updated 2 weeks ago
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 2 weeks ago
- A resilient distributed training framework☆96Updated last year
- torchcomms: a modern PyTorch communications API☆302Updated this week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆246Updated last year
- Perplexity open source garden for inference technology☆295Updated this week
- ACT An Architectural Carbon Modeling Tool for Designing Sustainable Computer Systems☆43Updated 4 months ago
- LLM Serving Performance Evaluation Harness☆82Updated 9 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆263Updated last month
- A large-scale simulation framework for LLM inference☆491Updated 4 months ago
- Fast low-bit matmul kernels in Triton☆402Updated 3 weeks ago
- Microsoft Collective Communication Library☆66Updated last year
- A low-latency & high-throughput serving engine for LLMs☆454Updated last month
- Perplexity GPU Kernels☆536Updated last month
- A curated list of awesome projects and papers for distributed training or inference☆258Updated last year
- 🔮 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☆154Updated 2 weeks ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆133Updated last year
- extensible collectives library in triton☆91Updated 8 months ago
- A library to analyze PyTorch traces.☆443Updated 3 weeks ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆345Updated this week
- ☆79Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆446Updated 6 months ago
- Multi-Instance-GPU profiling tool☆58Updated 2 years ago
- ☆48Updated last year
- Collection of kernels written in Triton language☆173Updated 8 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆120Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆227Updated 2 years ago
- Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)☆455Updated last week
- Stateful LLM Serving☆89Updated 9 months ago