Compiling LLMs into a MegaKernel: A path to low-latency inference (zhihaojia.medium.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of zhihaojia.medium.com: Compiling LLMs into a MegaKernel: A path to low-latency inference

First screen, captured 1 year ago.

Looks similar

Screenshot of medium.com: Local LLM inference – impressive but too hard to work with

Local LLM inference – impressive but too hard to work with (medium.com)

63 points by aazo11 1 year ago | 49 comments

Screenshot of medium.com: Why LLMs Can't Write Q/Kdb+: Writing Code Right-to-Left

Why LLMs Can't Write Q/Kdb+: Writing Code Right-to-Left (medium.com)

176 points by gabiteodoru 1 year ago | 124 comments

Screenshot of ai.gopubby.com: Run 70B LLM Inference on a Single 4GB GPU with This New Technique

Run 70B LLM Inference on a Single 4GB GPU with This New Technique (ai.gopubby.com)

80 points by gardenfelder 2 years ago | 39 comments

Screenshot of medium.com: Exploring LoRA – Part 1: The Idea Behind Parameter Efficient Fine-Tuning

Exploring LoRA – Part 1: The Idea Behind Parameter Efficient Fine-Tuning (medium.com)

139 points by aquastorm 1 year ago | 12 comments

Screenshot of neuecc.medium.com: “ZLinq”, a Zero-Allocation LINQ Library for .NET

“ZLinq”, a Zero-Allocation LINQ Library for .NET (neuecc.medium.com)

245 points by cempaka 1 year ago | 81 comments

Screenshot of donraab.medium.com: 10B Integers Walk into an Array

10B Integers Walk into an Array (donraab.medium.com)

32 points by ingve 2 years ago | 12 comments