Skip to content
Aditya Karnam
AI researcher building the infrastructure layer for reliable agents.

local-llms

View all tags
The Batch Size That Breaks Local LLM Serving on Apple Silicon

— ai, local-llms, open-source

Why Batching Doesn't Fix Decode: GEMV vs GEMM on Apple Silicon

— ai, local-llms, open-source

MLX Errors on Apple Silicon: A Reference

— ai, local-llms, open-source

Why MLX Decode Slows at Long Context

— ai, local-llms, open-source

Ollama vs vLLM vs SGLang on Apple Silicon

— ai, local-llms, evals, open-source

subagent-fleet: Local AI Compute Control Plane for Coding Agents

— ai, agents, open-source, local-llms

© 2026 Aditya Karnam. AI Researcher.
NowStackField NotesCurrent SystemsStatus