ml-energy / leaderboard-v2Links
A canonical source of GenAI energy benchmark and meausrements
☆50Updated last month
Alternatives and similar repositories for leaderboard-v2
Users that are interested in leaderboard-v2 are comparing it to the libraries listed below
Sorting:
- Measure and optimize the energy consumption of your AI applications!☆326Updated last week
- A resilient distributed training framework☆96Updated last year
- ☆25Updated 2 years ago
- End-to-end carbon footprint mod- eling tool☆51Updated 7 months ago
- LLM Serving Performance Evaluation Harness☆82Updated 10 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆93Updated 2 years ago
- Surrogate-based Hyperparameter Tuning System☆27Updated 2 years ago
- ACT An Architectural Carbon Modeling Tool for Designing Sustainable Computer Systems☆44Updated 5 months ago
- ☆89Updated 3 years ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆136Updated last year
- ☆48Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Updated last year
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆69Updated last year
- LLM checkpointing for DeepSpeed/Megatron☆22Updated last month
- ☆20Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆50Updated 5 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆206Updated last year
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated last year
- A minimal implementation of vllm.☆64Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆66Updated last year
- ☆94Updated 3 years ago
- Python package for rematerialization-aware gradient checkpointing☆27Updated 2 years ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆43Updated 3 years ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆73Updated last year
- ☆39Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆35Updated 3 years ago
- ☆81Updated 2 months ago
- Compression for Foundation Models☆35Updated 5 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆269Updated 2 months ago
- Easy, Fast, and Scalable Multimodal AI☆83Updated last week