Model selection
Building logic that chooses a suitable model for constrained devices and practical deployment settings.
Projects
A focused view of the engineering work behind Santosh M, including the Adaptive LLM Inference Engine built for efficient local AI systems.
Adaptive LLM Inference Engine
An engineering project focused on efficient local AI inference, model selection, and quantization for resource-constrained systems.
Quantization focus
Reducing model footprint while keeping the workflow grounded in efficient runtime decisions.
Focus
Local AI execution
Practical work aimed at keeping inference efficient on smaller systems.
Scope
Engineering depth
A project that shows how software engineering and AI development come together in one build.
Work detail
What this work emphasizes
The project page keeps the focus on the technical problem, the constraints, and the engineering judgment involved in the build.
Constraint
Resource-aware design
The project centers on making AI work within limited compute and memory budgets.
Engineering
Clear implementation choices
Model selection and quantization are presented as practical tools for better runtime behavior.