Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

A comparison of traditional RAG vs Graph RAG to see whether the results are better

mech-interp suite for Granite4 models that use Mamba-2 architecture

Systematic study of LoRA fine-tuning strategies for IBM Granite 4.0-H-Micro (Mamba-2 + Transformer hybrid). Demonstrates the impact of architecture-aware target selection and SSM core parameter co-training, including analysis of PEFT serialization behavior. Reports up to 37% relative improvement over LoRA-only baselines.