monarch-initiative / namo Star 16 Code Issues Pull requests standards artificial-intelligence ontologies monarchinitiative obofoundry organoids linkml new-approach-methodologies ai4curation model-systems Updated Dec 8, 2025 Python
manishklach / gpu-resident-inference-lab Star 1 Code Issues Pull requests Research lab for GPU-resident LLM inference loops: persistent kernels, sparse KV selection, tiered residency, speculative decode, and trace-driven scheduling. runtime cuda kv-cache gpu-systems llm-inference speculative-decoding model-systems persistent-kernel mega-kernel Updated Jun 13, 2026 Python