Andrew Fairless – Page 14 – Andrew Fairless, Ph.D.

What I Read: vectorize wide PyTorch expressions

By Andrew Fairless on January 16, 2024November 7, 2023

https://probablymarcus.com/blocks/2023/10/19/vectorizing-wide-pytorch-expressions.html What happens when you vectorize wide PyTorch expressions?Marcus Lewis19 October 2023 “So we see that vectorization has three effects:It lets us keep the GPU busy even when inputs areContinue readingWhat I Read: vectorize wide PyTorch expressions

What I Read: GPU Computing

By Andrew Fairless on January 15, 2024November 7, 2023

https://codeconfessions.substack.com/p/gpu-computing What Every Developer Should Know About GPU ComputingAbhinav UpadhyayOct 18, 2023 “GPUs have become incredibly important because of their pervasive use in deep learning. Today, it is essential forContinue readingWhat I Read: GPU Computing

What I Read: Enterprise AI, RAG + Fine Tuning

By Andrew Fairless on January 11, 2024November 20, 2023

https://www.montecarlodata.com/blog-the-moat-for-enterprise-ai-is-rag-fine-tuning/ The Moat for Enterprise AI is RAG + Fine Tuning – Here’s WhyLior GavishUpdated Nov 09 2023 “Data needs to be secure and private; LLM deployment needs to beContinue readingWhat I Read: Enterprise AI, RAG + Fine Tuning

What I Read: Compiling NumPy

By Andrew Fairless on January 10, 2024November 7, 2023

https://pytorch.org/blog/compiling-numpy-code/ Compiling NumPy code into C++ or CUDA via torch.compileby Evgeni Burovski, Ralf Gommers and Mario LezcanoOctober 17, 2023 “This feature leverages PyTorch’s compiler to generate efficient fused vectorized codeContinue readingWhat I Read: Compiling NumPy

What I Read: Neural algorithmic reasoning

By Andrew Fairless on January 9, 2024November 7, 2023

https://thegradient.pub/neural-algorithmic-reasoning/ Neural algorithmic reasoningPetar Veličković14.Oct.2023 “…we will talk about classical computation… Think shortest path-finding, sorting, clever ways to break problems down… we will also investigate how to capture such computationContinue readingWhat I Read: Neural algorithmic reasoning

What I Read: SAT Solvers

By Andrew Fairless on January 8, 2024November 7, 2023

https://www.borealisai.com/research-blogs/tutorial-9-sat-solvers-i-introduction-and-applications/ Tutorial #9: SAT Solvers I: Introduction and applicationsS. PrinceNov. 10, 2020 “This tutorial concerns the Boolean satisfiability or SAT problem…. we’ll show how to fit both neural networks andContinue readingWhat I Read: SAT Solvers

What I Read: Multimodality

By Andrew Fairless on January 4, 2024November 7, 2023

https://huyenchip.com/2023/10/10/multimodal.html Multimodality and Large Multimodal Models (LMMs)Chip HuyenOct 10, 2023 “For a long time, each ML model operated in one data mode… However, natural intelligence is not limited to justContinue readingWhat I Read: Multimodality

What I Read: Finetuning LLMs with LoRA and QLoRA

By Andrew Fairless on January 3, 2024November 7, 2023

Finetuning LLMs with LoRA and QLoRA: Insights from Hundreds of Experiments Finetuning LLMs with LoRA and QLoRA: Insights from Hundreds of ExperimentsSebastian RaschkaOctober 12, 2023 “LoRA is one of theContinue readingWhat I Read: Finetuning LLMs with LoRA and QLoRA

What I Read: Understanding Moments

By Andrew Fairless on December 21, 2023November 7, 2023

https://gregorygundersen.com/blog/2020/04/11/moments/ Understanding MomentsGregory Gundersen11 April 2020 “Why are a distribution’s moments called “moments”? How does the equation for a moment capture the shape of a distribution? Why do we typicallyContinue readingWhat I Read: Understanding Moments

What I Read: Distributed Training, Finetuning

By Andrew Fairless on December 20, 2023November 7, 2023

https://sumanthrh.com/post/distributed-and-efficient-finetuning/ Everything about Distributed Training and Efficient FinetuningSumanth R HegdeLast updated on Oct 13, 2023 “practical guidelines and gotchas with multi-GPU and multi-node training”

Author: Andrew Fairless