77 posts published
MLOps Part 10: A comprehensive guide to model compression covering knowledge distillation, low-rank factorization, and quantization, followed by ONNX and ONNX Runtime as the bridge from training frameworks to fast, portable production inference.
MLOps Part 9: A deep dive into model fine-tuning and compression, specifically pruning and related improvements.
MLOps Part 8: A systems-first guide to model development and optimizing performance with disciplined hyperparameter tuning.
MLOps Part 7: An applied look at distributed data processing with Spark and workflow orchestration and scheduling with Prefect.
MLOps Part 6: A deep dive into sampling, class imbalance, and data leakage; plus a hands-on Feast feature store demo.
MLOps Part 5: A detailed walkthrough of data engineering for MLOps, covering data sources, format performance trade-offs, and ETL/ELT pipelines.
MLOps Part 4: A practical walkthrough of W&B-powered reproducibility.
MLOps Part 3: A practical exploration of reproducibility and versioning, covering deterministic training, data and model versioning, and experiment tracking.
MLOps Part 2: A deeper look at the ML lifecycle, plus a minimal train-to-API and containerization demo using FastAPI and Docker.
MLOps Part 1: An introduction to machine learning in production, covering pitfalls, system-level concerns, and an overview of the full ML lifecycle.
MCP Part 9: Building a full-fledged research assistant with MCP and LangGraph.
..powered with MCP + Tools + Memory + Observability.
MCP Part 8: Integration of the model context protocol (MCP) with LangGraph, LlamaIndex, CrewAI, and PydanticAI.
MCP Part 7: A deep dive into understanding sandboxing and its need in MCP.
MCP Part 6: An overview of testing using the MCP Inspector, and a discussion of common vulnerabilities, mitigation strategies, and MCP Roots.
MCP Part 5: A deep dive into sampling, its working, code, use cases and best practices.
MCP Part 4: An in-depth exploration of MCP resources and prompts, followed by a hands-on demonstration of an MCP server utilizing tools, resources, and prompts for job search and analysis.
MCP Part 3: A step-by-step and from scratch implementation of the MCP client, plus a comparative overview of how MCP differs from both API and function calling.
MCP Part 2: An overview of key MCP primitives (capabilities), the MCP communication protocol and hands-on examples.
MCP Part 1: An introduction to model context protocol (MCP), covering background, need and an overview of the architecture and operational mechanics.
A from-scratch implementation of Llama 4 LLM, a mixture-of-experts model, using PyTorch code.
AI Agents Crash Course—Part 14 (with implementation).
AI Agents Crash Course—Part 13 (with implementation).
AI Agents Crash Course—Part 12 (with implementation).
AI Agents Crash Course—Part 11 (with implementation).
AI Agents Crash Course—Part 10 (with implementation).
AI Agents Crash Course—Part 9 (with implementation).
AI Agents Crash Course—Part 8 (with implementation).
AI Agents Crash Course—Part 7 (with implementation).
AI Agents Crash Course—Part 6 (with implementation).
