Run LLMs on Windows Using Ollama
Run ChatGPT-style models locally on Windows using Ollama—no cloud dependency.
Blog
Writing & Technical Notes
Short, practical write-ups on hardware-aware AI, VLSI workflows, timing/power analysis, and signal processing. All posts are hosted on Medium for now.
Medium Articles
Featured: VLSI / AI Tools
Featured Posts
High-signal tutorials and practical workflows.
Setting Up an NVIDIA GPU for Deep Learning
Complete guide to installing CUDA/cuDNN and frameworks for deep learning workflows.
Delay Calculation & Static Timing Analysis (OpenSTA)
STA theory + real reporting workflows using OpenSTA for chip design.
All Posts
Chronological list of Medium articles.
Create an AI PoC as a Manager
Strategy + execution steps for building proof-of-concepts aligned to business goals.
Understanding Self-Attention in Transformers
A clean explanation of attention and multi-head attention for quick intuition.
Hands-On Power Analysis with OpenSTA
Power + delay analysis workflow with practical examples and reporting structure.
Running OpenSTA in Docker
Spin up OpenSTA quickly via Docker for repeatable, clean timing runs.
Logic Optimization with Yosys
Use Yosys passes to optimize RTL and improve downstream synthesis quality.
Logic Synthesis Tutorial with Yosys
Start-to-finish introduction to synthesis using an open-source flow.
Verilog Simulation with Icarus
Design + verify a synchronous counter using Icarus Verilog and waveforms.
Quick Links
Profiles and primary writing hub.
Topics
- Hardware-aware AI and efficient inference
- VLSI: timing, power, synthesis, verification
- Signal processing and RF workflows
- Practical tooling (Docker, OpenSTA, Yosys)