llmopsinferenceself-hosting
Serving open models with vLLM
Hands-on guide to self-hosting open-weights LLMs with vLLM: install, serve an OpenAI-compatible API, quantize, benchmark, and manage VRAM.
Writing
Blog
9 posts on building with AI.
All posts
mcpagentstools
Building an MCP server and wiring it to an agent
Build a typed MCP server in Python, run it over stdio and HTTP, wire it into Cursor, and drive it from a custom client and an OpenAI-compatible model.
asrnlpresearch
From 34% to 28% WER: lessons from code-switching ASR
What I learned building a Whisper + LLaMA speech recognizer for Malay–English code-switching — where the WER actually came from, and what didn't help.
edge-aideploymentsdv
Shipping a model to the edge: PyTorch → ONNX → TensorRT
A hands-on, current (2026) path for taking a PyTorch CV model to ONNX and a TensorRT engine: export, parity, FP16/INT8 build, and latency gating.
ragagentsretrieval
Agentic RAG: retrieval that decides for itself
Build agentic RAG in Python: hybrid retrieval as a tool, a bounded agent loop, sufficiency and grounding checks, against any OpenAI-compatible endpoint.
agentsragllmops
Lessons from shipping a multi-agent e-commerce assistant
Building an end-to-end multi-agent system — support, recommendation, and pricing — with LangChain, AutoGen, FastAPI, Kafka, and Qdrant. What held up and what I'd change.
fine-tuningtrainingllmops
Fine-tuning an open model with QLoRA
A hands-on QLoRA fine-tuning walkthrough: dataset prep, 4-bit training with peft and trl, merging, and vLLM serving behind an OpenAI-compatible API.
structured-outputtool-usejson
Structured outputs you can trust
A layered, runnable approach to reliable structured LLM outputs: pydantic schemas, json_schema enforcement, bounded validate-and-retry, and constrained decoding.
computer-visionresearch
Hybrid CNN + Vision Transformer for deepfake detection
Why combining CNNs, InceptionNeXt, and a Vision Transformer beat either alone for video deepfake detection — and why cross-dataset generalization is the metric that matters.