A from-scratch Prefill/Decode disaggregation inference engine for LLMs

Python Updated 7 months ago 1 commits 38 stars
pulse-dev|Mirror: HJCheng0602/nanoPD (⭐38)
7 months ago
E2B SandboxFirecracker microVMpython
No executable code files found in this repository.

About

A from-scratch Prefill/Decode disaggregation inference engine for LLMs

Readme
38 stars
4 forks