AI Repo
Stats
Repos
Categories
Developers
Countries
EN
efeslab/Nanoflow · AI Repo Stats
Repos
Categories
Developers
Countries
VI
EN
EF
efeslab/
Nanoflow
A throughput-oriented high-performance serving framework for LLMs
LLM & foundation models
Jupyter Notebook
55
created 2024-08-19
Website
GitHub
#cuda
#inference
#llama2
#llm
#llm-serving
#model-serving