Adnan Sattar·Aug 25From 140GB to 40GB: An Engineer’s Guide to LLM QuantizationWhy GGUF, GPTQ, AWQ, FP8, and SmoothQuant exist, what they actually do, and how to pick between them in production
InGoPenAIbyJatinkumar Parmar·Jul 23FP8 quantization with AMD Quark for vLLMAuthor: Charles Yang , Jatinkumar parmar Knowledge level: Intermediate
Nikulsinh Rajput·Oct 1, 2025FP8 + Structured Sparsity: Spend Less, Serve MoreCombine 8-bit floating point with 2:4 sparsity to cut GPU memory and flops — while keeping accuracy and p99s in check.
InAI Simplified in Plain EnglishbyFrank Morales Aguilera·Sep 2, 2025Precision, Power, and the Path to Superintelligence: The Impact of Floating-Point in AIFrank Morales Aguilera, BEng, MEng, SMIEEE
Rshravan·Aug 5, 2025PART 3 — MEMORY… IS THE REAL COMPUTEThis is a dramatized version of how things “may have” unfolded, intended to make core math, engineering concepts, and complicated ideas…A response icon1A response icon1
Adnan Masood, PhD.·Feb 20, 2025Bits and Business: FP8 quantization deepdive into DeepSeek’s High-Precision, Low-Bit RevolutionTim Dettmers of Making deep learning accessible, said something really profound and beautiful.
InFriendliAIbyFriendliAI Tech & Research·Apr 15, 2024Improve Latency and Throughput with Weight-Activation Quantization in FP8Quantization is a popular technique used to reduce the size of a machine learning model by lowering the numerical precision of some of its…
1kg·Jul 28, 2023FP8: Deep Learning’s New Power ToolLet’s take a journey into the realm of artificial intelligence, specifically deep learning. Here, we have immense structures, called neural…
