brave-experiments / MELT-publicLinks
codebase for "MELTing Point: Mobile Evaluation of Language Transformers"
☆18Updated 10 months ago
Alternatives and similar repositories for MELT-public
Users that are interested in MELT-public are comparing it to the libraries listed below
Sorting:
- One-size-fits-all model for mobile AI, a novel paradigm for mobile AI in which the OS and hardware co-manage a foundation model that is c…☆28Updated last year
- (HotMobile'24) Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing☆16Updated last year
- An LLM inference engine, written in C++☆15Updated 4 months ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆63Updated 11 months ago
- Federated Learning Systems Paper List☆73Updated last year
- Enhancing Efficiency in Multidevice Federated Learning through Data Selection☆13Updated last year
- Survey Paper List - Efficient LLM and Foundation Models☆248Updated 8 months ago
- Compression for Foundation Models☆31Updated 2 months ago
- Libraries for efficient and scalable group-structured dataset pipelines.☆26Updated 5 months ago
- How much energy do GenAI models consume?☆42Updated 3 weeks ago
- ☆30Updated last year
- Source code and datasets for Ekya, a system for continuous learning on the edge.☆105Updated 3 years ago
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆29Updated 6 months ago
- A resilient distributed training framework☆95Updated last year
- ☆99Updated last year
- Videoconferencing research platform☆65Updated 7 months ago
- [DMLR 2024] FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things☆55Updated 9 months ago
- ☆201Updated last year
- ☆46Updated 11 months ago
- a curated list of high-quality papers on resource-efficient LLMs 🌱☆122Updated 2 months ago
- ☆23Updated last year
- Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"☆140Updated last year
- Federated Few-shot Learning for Mobile NLP. Conditionally accepted by MobiCom'23.☆16Updated last year
- ☆94Updated 2 years ago
- ☆43Updated 2 weeks ago
- Implementation for FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients☆20Updated 9 months ago
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆32Updated last year
- ☆13Updated last year
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆108Updated 7 months ago
- Miro[ACM MobiCom '23] Cost-effective On-device Continual Learning over Memory Hierarchy with Miro☆15Updated last year