Gururaj Narayanan·Oct 25How do LLMs execute Tools or functions ?When working with LLMs, “invoking tools” or “invoking functions” is often abstracted away. You pass a list of functions to an SDK, the…
Gururaj Narayanan·Oct 2Split Walnut ( Brain)The title was fun or click bait but the topic is serious ! Let’s jump into it.
Gururaj Narayanan·Sep 26Cost of Faster WritesWe come across multiple systems that allow faster writes. In many systems, there is a trade-off where some of the cost of these faster…
Gururaj Narayanan·Sep 19Memory for low latency reads and writesSystem design must leverage node memory to achieve sub-ms read/write latencies, backed by guardrails against data loss. Distributed systems…
Gururaj Narayanan·Sep 7Why Apache Kafka is So Fast: A Simple ExplanationWe know Kafka is extremely fast and handles huge amounts of data without slowdowns. Kafka stays simple and lets the OS do the hard work.
Gururaj Narayanan·Mar 27Uber’s approach to Rate Limiter: Architectural Evolution and Trade-offsUber has 1000s of microservices making millions of RPCs between them and there was definitely a need for a rate limiter so that services…
Gururaj Narayanan·Mar 11Netflix Real Time Distributed Graph — Example of how tradeoffs are doneProblem:
Gururaj Narayanan·Apr 21, 2024The Critical Role of Preprocessing in Low Latency ExperiencesThere are several common scenarios where users expect instant responses or low latency experiences:
Gururaj Narayanan·Apr 13, 2024Replication — Chaotic GoodnessReplication is a powerful tool, offering numerous benefits. However, it’s essential for users to be aware of potential challenges and…
Gururaj Narayanan·Apr 6, 2024Big data and systems that process it.In the era of big data, there exists a vast amount of data, both structured and semi-structured, requiring efficient systems capable of…