Het Trivedi·Feb 19What I Got Wrong About Working At An AI StartupWhen I joined an AI startup, I was mostly excited about learning all of the technical bits. I thought I would be able to elevate my core…
InTDS ArchivebyHet Trivedi·Aug 27, 2024Boosting LLM Inference Speed Using Speculative DecodingA practical guide on using cutting-edge optimization techniques to speed up inference
InTDS ArchivebyHet Trivedi·Jun 25, 2024Improving RAG Performance Using RerankersA tutorial on using rerankers to improve your RAG pipelineA response icon1A response icon1
Het Trivedi·Jun 2, 2024What I Learned As A Forward Deployed Engineer Working At An AI StartupIn January 2024, I started working full-time as a forward deployed engineer at a company called Baseten. Baseten enables customers to…A response icon3A response icon3
InTDS ArchivebyHet Trivedi·Feb 22, 2024Deploying LLMs Into Production Using TensorRT LLMA guide on accelerating inference performanceA response icon5A response icon5
InLevel Up CodingbyHet Trivedi·Nov 1, 2023Deploying Codellama As A REST API ServiceIntroductionA response icon1A response icon1
InLevel Up CodingbyHet Trivedi·Oct 6, 2023Creating AI Generated QR Codes Using Stable Diffusion And ControlNetGenerate awesome looking QR codes using AI and Python
InTDS ArchivebyHet Trivedi·Aug 9, 2023Increase Llama 2's Latency and Throughput Performance by Up to 4XReal-world benchmarks for Llama-2 13BA response icon4A response icon4
InThe GeneratorbyHet Trivedi·Jul 31, 2023The Witcher’s Scripting Sorcery: Empowering The TV Adaptation With Large Language ModelsRecreating A TV Show Script For The Witcher Based On The Books
InTDS ArchivebyHet Trivedi·Jul 7, 2023Deploying Falcon-7B Into ProductionRunning Falcon-7B in the cloud as a microserviceA response icon6A response icon6