Problem Statement Solana, the famed permission-less blockchain, relies on a crafty transaction processing engine known as the Sealevel runtime. Sealevel allows hyper-parallelized processing of transactions submitted to the chain, in turn enabling a high TPS (Transactions Per Second) figure. Parallel processing of transactions??? What??? Is that possible??? Yes. But if and only…

ERC-4337 is being touted as Ethereum’s most awaited “UX Upgrade”. But why? Motivation If you’ve ever tried to build Web3 apps with amazing user experiences you’ll eventually hit road blocks that are imposed by the limitations of an EOA. In other words, the UX ceiling in terms of what you can…

Learn how to decide what topics and partitions to include in Redpanda — Let’s continue the conversation. Here’s a little recap: We are building a cryptocurrency arbitrage platform and we need to get streaming price updates from all the DEXs/CEXs/AMMs for each token pair being traded on them, and for each update, we need to run an algorithm to detect any arbitrage opportunity. …

No, this post is not sponsored by Redpanda (yet) — Last year we were building an ambitious “cryptocurrency arbitrage platform”, which, simply put, is basically buying crypto apples for $5 from some market, then selling them for $5 worth of crypto bananas from another market which then sold for $10 worth of crypto apples in yet another market. It sounds…

Learn how to extend Triton’s Kaldi backend to support multiple GPUs Let’s get deep in the weeds. The problem was that the client had an Automated Speech Recognition (ASR) Model that he wanted to deploy on scale. …

Find out how Triton solves the most common pain points of serving DL Models — MLops is a wild world. Everybody has their own pipelines with different tradeoffs, and it’s usually much better than having nothing. A fan favorite for model deployment though is Nvidia’s Triton. It’s kind of difficult to work with but the right expert can help you get your serving pipeline off…