#inference-optimization

GenAI Career Roadmap 2026 🚀 | AI Job Paths & Skills Guide

Kimi K3 (2.8T/A50B) inference on 8x H200 — evaluation baseline via the unsloth llama.cpp fork. Forked from gittensor-ai-lab/sparkinfer.

A controller that learns how a tool-using agent should spend compute at each step (WIDER, DEEPER, DECOMPOSE, STOP, or ESCALATE to a stronger model) and improves its own policy from logged traces. Judged on cost per solved task with paired statistics; ships trained policies and an offline embed API (pip install, no key needed).