https://www.ahmadosman.com/ Recent content on Osman's Odyssey: Byte & Build https://www.ahmadosman.com/logo/byte-and-build.png https://www.ahmadosman.com/logo/byte-and-build.png Hugo -- 0.145.0 en-us Thu, 26 Jun 2025 14:35:54 -0500 https://www.ahmadosman.com/blog/first-came-the-tokenizer/ Thu, 26 Jun 2025 14:35:54 -0500 https://www.ahmadosman.com/blog/first-came-the-tokenizer/ A deep dive into tokenizers, the invisible first piece of your LLM stack. Learn how they control costs, context windows, and performance, and see how algorithms like BPE and SentencePiece can make or break your AI. https://www.ahmadosman.com/blog/learn-llms-roadmap/ Mon, 23 Jun 2025 13:02:02 -0500 https://www.ahmadosman.com/blog/learn-llms-roadmap/ The straight-up, no-BS roadmap for learning LLMs in 2025. Skip the ML fluff and endless prerequisites. Get the actionable phases, projects, and resources to actually build, train, and ship large language models—from the ground up. https://www.ahmadosman.com/blog/software-engineers-arent-getting-automated-local-ai-has-to-win/ Sat, 21 Jun 2025 07:08:00 -0500 https://www.ahmadosman.com/blog/software-engineers-arent-getting-automated-local-ai-has-to-win/ Stop worrying about AI replacing you—the real threat is losing technical depth. As cloud dependence grows and platforms get more opaque, local-first AI, open weights, and full-stack ownership are the only safety nets left. Why the future belongs to those who can build, debug, and own their tools from the metal up. Trust no corporate overlord. https://www.ahmadosman.com/blog/my-ultimate-deepresearch-prompt-builder/ Fri, 20 Jun 2025 03:06:06 -0500 https://www.ahmadosman.com/blog/my-ultimate-deepresearch-prompt-builder/ I’m sharing my DeepResearch prompt builder template—the system that powers my research and learning workflows. Learn exactly how I turn chaos into clarity, force actionable insights, and get the most out of LLMs. See the template, my step-by-step process, and real-world tips for DeepResearchMaxxing in 2025. https://www.ahmadosman.com/blog/just-like-gpus-we-need-to-be-stress-tested-101-days-of-blogging/ Wed, 18 Jun 2025 23:02:02 -0500 https://www.ahmadosman.com/blog/just-like-gpus-we-need-to-be-stress-tested-101-days-of-blogging/ Why 101 days of daily tech blogging? A raw, open challenge on AI, LLMs, self-hosted experiments, knowledge distillation, and why consistency beats talent. Expect rants, technical breakdowns, open hardware journeys, memes, and daily accountability from the basement AI server guy. https://www.ahmadosman.com/blog/mastering-the-corporate-game-space/ Fri, 02 May 2025 14:44:44 -0500 https://www.ahmadosman.com/blog/mastering-the-corporate-game-space/ Corporate politics isn't just backroom deals—it's how influence, visibility, and relationships shape your career. In this candid guide, you'll learn to use titles, politics, and intentional networking to your advantage (without selling your soul). Real talk from people who've played—and won—the game at big tech and beyond. https://www.ahmadosman.com/blog/once-undesirable-now-undeniable/ Wed, 30 Apr 2025 15:46:46 -0500 https://www.ahmadosman.com/blog/once-undesirable-now-undeniable/ How taking risks, building in public, and refusing to play a losing game flipped the script—and why sometimes you have to become undeniable before you ever become accepted. https://www.ahmadosman.com/blog/build-your-local-privat-ai-screenshot-organizer-with-lmstudio/ Tue, 22 Apr 2025 08:56:56 -0500 https://www.ahmadosman.com/blog/build-your-local-privat-ai-screenshot-organizer-with-lmstudio/ Build a local, privacy-first screenshot organizer using LMStudio’s Python SDK and Gemma 3 multimodal models. Keep your data off the cloud, automate screenshot categorization, and leverage the power of open-source AI—all running from your own PC. Step-by-step guide, code walkthrough, and a practical use-case for local LLMs. https://www.ahmadosman.com/blog/no-rag-is-not-dead-space/ Fri, 11 Apr 2025 15:31:31 -0500 https://www.ahmadosman.com/blog/no-rag-is-not-dead-space/ Forget the hype—here’s what actually happened when we asked “Is RAG dead?” This deep-dive explores why Retrieval-Augmented Generation (RAG) is still essential in real AI systems, what people get wrong, and how practitioners are shipping the next wave of AI with smarter retrieval, dynamic context, and hard-earned lessons from the field. https://www.ahmadosman.com/blog/from-the-shadows-to-the-feed/ Tue, 25 Mar 2025 14:28:28 -0500 https://www.ahmadosman.com/blog/from-the-shadows-to-the-feed/ After years of building in the dark, I decided to play the game of distribution. Here’s why networks—and distribution—matter more than ever, and why I’m finally sharing my journey, experiments, and ideas in public. https://www.ahmadosman.com/blog/r1-ktransformers-inference-livestream/ Fri, 14 Feb 2025 02:56:56 -0600 https://www.ahmadosman.com/blog/r1-ktransformers-inference-livestream/ Key takeaways from livestreaming DeepSeek R-1 671B (4-bit) on a 14x RTX 3090 basement AI server. See how KTransformers crushed llama.cpp in prompt eval speeds, compare setups, and get real-world insights into massive LLM inference with vLLM, ExLlamaV2, and more. https://www.ahmadosman.com/blog/do-not-use-llama-cpp-or-ollama-on-multi-gpus-setups-use-vllm-or-exllamav2/ Fri, 07 Feb 2025 05:06:36 -0600 https://www.ahmadosman.com/blog/do-not-use-llama-cpp-or-ollama-on-multi-gpus-setups-use-vllm-or-exllamav2/ Exploring the intricacies of Inference Engines and why llama.cpp should be avoided when running Multi-GPU setups. Learn about Tensor Parallelism, the role of vLLM in batch inference, and why ExLlamaV2 has been a game-changer for GPU-optimized AI serving since it introduced Tensor Parallelism. https://www.ahmadosman.com/blog/deepseek-r1-space/ Sun, 02 Feb 2025 15:35:35 -0600 https://www.ahmadosman.com/blog/deepseek-r1-space/ A curated collection of links, books, tools, and benchmarks discussed during the February 2nd, 2025 Twitter/X Audio Space on LLMs and AI. Includes practical resources, RAG leaderboards, toolkits, and perspectives on AI adoption in the Middle East and globally. https://www.ahmadosman.com/blog/taleb-antifragile-ai-insights/ Tue, 03 Dec 2024 04:21:55 -0600 https://www.ahmadosman.com/blog/taleb-antifragile-ai-insights/ Explore how AI systems can become antifragile, harnessing uncertainty to thrive. Learn about the shift and acceleration from traditional software to AI agentic systems and their implications for the future. https://www.ahmadosman.com/blog/go-all-in/ Tue, 01 Oct 2024 22:08:52 -0500 https://www.ahmadosman.com/blog/go-all-in/ Embrace new ideas, trust your instincts, and go all in. 42 days to launch—let’s win this game! #GoAllIn https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-ii/ Wed, 18 Sep 2024 05:57:26 -0500 https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-ii/ SWE Agentic Framework, MoEs, Quantizations & Mixed Precision, Batch Inference, LLM Architectures, vLLM, DeepSeek v2.5, Embedding Models, and Speculative Decoding: An LLM Brain Dump... I have been working on a multi-agent system that simulates a team of Software Engineers; this system assigns projects, creates teams and adds members to them based on areas of expertise and need, and asks team members to build features, assign story points, have pair programming sessions together, etc. https://www.ahmadosman.com/about/ Fri, 06 Sep 2024 17:54:23 -0500 https://www.ahmadosman.com/about/ Hi There! 👋 Welcome to my corner of the internet where every line of code, every 3D printed layer, and every gym rep is a brushstroke on the canvas of creation. By trade, I’m a software engineer, but really, I’m a perpetual learner; a builder; a problem solver; a creator; a thinker; and a tinkerer in the grand workshop of life. Bit By Bit: The Journey & The Camels Born and raised on the the Egyptian Nile, I come from a middle-class family that did its best to allow me to do the things I do today. I started coding at 7. Basic HTML site with a flashy mouse pointer and glitters everywhere. At 12 I wrote my first server-sided application to host my private MMORPG server of a very popular game. The Rise Of a Cyber Mogul’s Prodigy 🤔 This MMORPG server was written in C++, and it ran on my Pentium 4 desktop, which had 256KB of ram, and needed a VPN network for connections to go through as I did not have a static IP address. If I remember correctly, the VPN name was Hamachi. At peak times I used to limit the number of players on the server to ~30, otherwise my PC would get the Blue Screen of Death. At some point I wrote a script to remove players, send warnings, etc, using a queue during peak time. I distributed the game at local internet cafés where people typically played on the official servers. But my version offered something unique—easier award systems, quicker leveling up, more PvP events scheduled around local time, premium gears, Game Master privileges, and Player Master statuses. Players on the server started asking me if they could pay for these things to get them quicker, so I put a price tag on some of them. Funny enough, the server attracted most of its players from an area ~160 miles away from where I lived, so most of my “sales” came in the form of prepaid phone credit. The server was online for only a few months, but I made enough prepaid phone credit to cover me for the next 4 years. Talk about feeling like a tech tycoon at 12. Going International I completed my high school education in the Netherlands, where I not only pursued an International Baccalaureate degree but also managed to crowdfund $50,000 USD to bridge the gap left by a partial scholarship. Following this, I was awarded a full scholarship to Luther College in Decorah, IA, where I earned my BAs in Computer Science and Data Science. I have held several positions over the years, I am Ex-Mayo Clinic, Trimble, Fed. HLBDM, and CloudInn, and currently I am on an adventure to my next big thing. 😉😉 In The Digital Realm My work isn’t just about writing code; it’s about crafting solutions that push the boundaries of what’s possible in technology. The essence of software is crafting something of value, giving people a tool that enhances their daily lives, and doing that with the least amount of friction possible. My approach is product-centric focusing on designing excellent scalable systems. On the day-to-day basis, my days are mostly a whirlwind of coding, often wrestling with AI models to do my bidding (sometimes they cooperate, sometimes they don’t, but it’s always an adventure), and solving data puzzles to uncover hidden patterns. While I’m deeply focused on the wizardry that is software engineering, my passion also spills over into the physical world where I self-host my own infrastructure because, why not control the cloud from your living room? Building Beyond the Binary In the physical world my home lab might just be the next tech startup incubator, or at least, that’s what I tell myself as it slowly conquers my living space (yes, I get the eye-rolls, but deep down, I know everyone loves it). When I’m not buried in lines of code or training models, you’ll find me in my home lab, tinkering with 3D printers, upgrading a server, conjuring up hardware projects, or playing network wizard with my clusters. AI & Iron: A Personal Odyssey My life is an odyssey of merging the digital with the physical. I see parallels between training neural networks and training my body. Both require discipline, patience, and a willingness to adapt and learn. This journey has taught me the value of resilience, not just in AI algorithms but in personal growth. Every rep in the gym, every line of code, every piece of data analyzed is a step towards becoming a better version of myself. I sincerely believe that true excellence starts from health, and I treat physical fitness with the same enthusiasm as my projects, and then some. Pages and Pause I have two types of downtime. One is where I pull out any book that catches my eye from my collection, leaf through it randomly, stopping when something grabs my attention, and then I settle in to read. The other involves savoring a cup of coffee, a ritual that serves as my quiet time for reflection, where I contemplate life and things, dream up new projects, or simply enjoy the moment. Code, Create, and Conquer This website is more than a portfolio; I intend for it to be a showcase of my journey. For all intents and purposes, this will be my digital journal where I dive into technology, artificial intelligence, hardware, and growth, among other things; offering readers a glimpse into my thoughts and discoveries. Adjacent to this, I intend to have a projects section that will act as a virtual gallery, showcasing an array of my endeavors from intricate software solutions and advanced AI models to creative 3D printing projects, with each piece narrating its own tale of innovation. Thank you for visiting. Here’s to coding, lifting, learning, and everything in between. The future is ours to take, let’s build and achieve great things. “A man who views the world the same at 50 as he did at 20 has wasted 30 years of his life.” ― Muhammad Ali P.S. 🐫🐫🐫 Oh, and yes, I’ve never actually ridden a camel, but I’ve gotten close enough to smell their less-than-fragrant breath and decide it wasn’t worth it. Contrary to popular belief—based solely on my highly unscientific observations and experiences—there are actually quite a few cars in Egypt. Who knew the pyramids had such great parking? https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-i/ Fri, 06 Sep 2024 16:37:23 -0500 https://www.ahmadosman.com/blog/serving-ai-from-the-basement-part-i/ Dedicated LLM server powered by 8x RTX 3090 Graphic Cards, boasting a total of 192GB of VRAM.