7 projects
runinfra
RunInfra SDK for optimized inference deployments across text, embeddings, image, and audio routes
tide-inference
Token-Informed Depth Execution — dynamic per-token layer skipping for transformer inference
gpuci
Test CUDA kernels across multiple GPUs via SSH
EvoloPy
An open source nature-inspired optimization toolbox with parallel processing capabilities
JrKit
JR's Advanced Encoding Toolkit: Innovative encoding methods for data representation and feature extraction