PinnedSiddharth Parmar (Sid)·Mar 4How LLM Inference Got 10x CheaperHow the field slashed LLM inference costs through attention redesigns, IO-aware computation, KV cache paging, and speculative decoding, and…
Siddharth Parmar (Sid)·Feb 11AI Agents, MCP Tools, and Skills: Toward Smarter WorkflowsWhy naive MCP usage breaks at scale, how code execution fixes context bloat, and how skills turn agent workflows into reusable building…
Siddharth Parmar (Sid)·Oct 23, 2025Making LLMs Efficient in ProductionA practical journey to deploy faster, cheaper LLM/transformer models using distillation, quantization, and ONNX Runtime — no PhD required.
Siddharth Parmar (Sid)·Oct 16, 2025From Perfect Prompts to Perfect IngredientsHow Anyone Can Guide AI Without Being a Techie.
Siddharth Parmar (Sid)·Oct 8, 2025Transformers: Simple Yet Wildly VersatileHow a simple attention-only architecture scaled from translation to language, vision, code, and diffusion.
Siddharth Parmar (Sid)·Sep 29, 2025The Days of Prompt Engineering Are OverMy day-to-day shifted from prompt phrasing to context-first workflows — feeding the model code, docs, and tickets to drive reliable…
Siddharth Parmar (Sid)·Sep 29, 2025Building a Unified Orchestrator for Agentic Flow with A2A + MCPArchitecture notes on bridging A2A and MCP toolchains through a single streaming orchestrator.
Indev@redbySiddharth Parmar (Sid)·Sep 11, 2018async-react: A React component to simplify data fetchingIn this post, I am going to talk about a new JavaScript library that I created. It is called async-react.
Indev@redbySiddharth Parmar (Sid)·Aug 17, 2018Tutorial: Build an App with ReasonReactPart 2-Building a Basic To-Do AppA response icon1A response icon1
Indev@redbySiddharth Parmar (Sid)·Jul 24, 2018Tutorial: Build an App with ReasonReactPart 1-Future of React? ReasonReact!