@Venkat2811
Venkat Raman
@Venkat2811
Research & Engineering - LLM Inference & High Performance systems.
Berlin, GermanyJoined July 2022
About
🧑💻 Research & Engineering - LLM Inference & High Performance systems. |📍Berlin 🇩🇪 | 📚 https://venkat.eu | 💬 https://twitter.com/Venkat2811
Available for
Nothing here yet.
Venkat Raman's blogs
Recently published
Essential Math & Concepts for LLM Inference
May 31, 2024 · 12 min read · (Image Credit: HF TGI Benchmark) Introduction As enterprises and tech enthusiasts increasingly integrate LLM applications into their daily workflows, the demand for TFLOPS is ever increasing. Apple, Microsoft, Google, and Samsung have already introdu...
Join discussion
The power of Mechanical Sympathy in Software Engineering
Apr 18, 2024 · 22 min read · Introduction Modern software programming languages, compilers, and frameworks abstract away underlying complexities and details, allowing developers to focus on building systems and applications to solve business problems. This design enables enginee...
Join discussion
CPU & GPU - The Basics
Apr 8, 2024 · 16 min read · Introduction In this article, we'll go through some fundamental low level details to understand why GPUs are good at Graphics, Neural Network and Deep Learning tasks and CPUs are good at wide number of sequential, complex general purpose computing ta...
Join discussion
OS Error: Too many open files. Understanding file and socket descriptors.
Mar 26, 2024 · 7 min read · Intro Engineers who've built, deployed and operated backend services would've encountered this error. It usually means your service is serving real user requests - Yay 🎉 ! One possible scenario is - you need to fine-tune server OS configuration to s...
Join discussion