Optimization on Pranav Buradkar

Optimization on Pranav Buradkar https://pranavburadkar.github.io/tags/optimization/ Recent content in Optimization on Pranav Buradkar Hugo -- 0.164.0 en-us Mon, 27 Jul 2026 15:00:00 +0530 Demystifying Mixed Precision Training: Speeding Up Deep Learning with FP16 and BF16 https://pranavburadkar.github.io/posts/mixed-precision-training/ Mon, 27 Jul 2026 15:00:00 +0530 https://pranavburadkar.github.io/posts/mixed-precision-training/ An in-depth guide on how mixed precision training works, the mathematics of loss scaling, the difference between FP16 and BF16, and how to implement it in PyTorch. A Simple Guide to LLM Serving: Quantization, KV Caching, and Continuous Batching https://pranavburadkar.github.io/posts/understanding-llm-optimization/ Sun, 10 May 2026 10:00:00 +0530 https://pranavburadkar.github.io/posts/understanding-llm-optimization/ Dive into the three key techniques that make serving large language models (LLMs) fast, cheap, and memory-efficient. A Beginner's Guide to LLM Quantization: GGUF, GPTQ, and AWQ https://pranavburadkar.github.io/posts/beginners-guide-to-llm-quantization/ Thu, 20 Nov 2025 10:00:00 +0000 https://pranavburadkar.github.io/posts/beginners-guide-to-llm-quantization/ Expanding on LLM optimization by explaining how massive models are compressed using techniques like GGUF, GPTQ, and AWQ to run on consumer hardware.