HSHarshit Sharmainconnectai.blog·Apr 14 · 1 min readTurbo Quant : Visual Essay Serieshttps://turboquant-blogs.vercel.app/00
HSHarshit Sharmainconnectai.blog·Mar 15, 2025 · 2 min readAgents : Architecture and DesignThe term “agent” can have multiple interpretations. Some define agents as fully autonomous systems that operate independently over extended periods, leveraging various tools to complete complex tasks. Others use the term to refer to more structured i...00
HSHarshit Sharmainconnectai.blog·Mar 10, 2025 · 13 min readAgents : MemoryImplementing Long-Term Memory in AI Agents (Semantic, Episodic, Procedural) with LangMem AI agents powered by large language models (LLMs) can appear more intelligent and personalized when they remember information over time. By equipping agents with...00
HSHarshit Sharmainconnectai.blog·Mar 8, 2025 · 4 min readDeepGEMM: Clean and Efficient FP8 GEMM LibraryIntroduction DeepGEMM is a clean and efficient FP8 General Matrix Multiplication (GEMM) library with fine-grained scaling, released by DeepSeek as part of their "Open Source Week" in February 2025. It supports both normal dense GEMMs and Mixture-of-E...00
HSHarshit Sharmainconnectai.blog·Mar 5, 2025 · 5 min readUnderstanding Load Balancing and Expert Parallelism in AI ModelsExpert Parallelism Load Balancer (EPLB) In the world of AI and deep learning, managing the computational load efficiently is a critical task. Models, especially large-scale ones like those used in Natural Language Processing (NLP) or computer vision,...00
