inference-allocation

Here is 1 public repository matching this topic...

kadubon / split-inference-bench

Fixed-budget multi-agent inference benchmark harness for studying when split inference helps or hurts versus a strong single-agent baseline under local context ceilings, using local Ollama gemma3:1b, CPU-only pilots, topology diagnostics, verification-budget analysis, and reproducible experiment logging.

ai topology multi-agent-systems split-inference mixture-of-experts ai-evaluation llm-benchmark inference-allocation fixed-budget local-context experiment-harness

Updated Mar 12, 2026
Python

Add this topic to your repo

To associate your repository with the inference-allocation topic, visit your repo's landing page and select "manage topics."

Learn more