6 projects
drigs
Distributed Resource & Intelligent GPU Scheduling runtime for AI workloads
microgen-llm
Lightweight, modular, hardware-aware LLM inference engine & empirical research testbed.
sumospace
A locally-first, multi-agent autonomous task execution framework with zero cloud dependencies.
csaq-quant
Causal Salience-Aware Quantization — gradient×activation informed, clique-graph LLM weight quantization with self-speculative decoding
nikame
NIKAME: High-fidelity AI & Cloud Infrastructure Scaffolding Framework (Matrix Engine)
cleanpad
Text cleaner and formatter for handling messy copy-pasted content
