[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
-
Updated
Feb 11, 2025 - Python
[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Python 3.12 application for scaling images using various algorithms
Kernel objects for scaling and format conversion within VapourSynth
This repo focuses on latency-aware resource optimization for Kubernetes
contains the basic structure that a model serving application should have. This implementation is based on the Ray Serve framework.
Optimization algorithms and heuristics
Add a description, image, and links to the scaling-methods topic page so that developers can more easily learn about it.
To associate your repository with the scaling-methods topic, visit your repo's landing page and select "manage topics."